Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and phrases related to measurements, operations, or conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instructions, rules, or procedures

    np_acts-logits-general · gemini-2.0-flash

    guidelines, notes, or specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.77
     चीज़ों
    -0.65
    rungsseite
    -0.61
    ReusableCell
    -0.59
    tagHelperRunner
    -0.59
    SequentialGroup
    -0.58
    StructEnd
    -0.56
     للمعارف
    -0.56
    Становништво
    -0.55
    principalTable
    -0.55
    POSITIVE LOGITS
    ules
    0.52
    cales
    0.48
     stránky
    0.48
    ticks
    0.47
    teps
    0.43
     neler
    0.43
     themselves
    0.42
    mbals
    0.42
    ULES
    0.42
    ights
    0.41
    Act Density 1.702%

    No Known Activations