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

    Neuronpedia

    INDEX
    Explanations

    structured data or tabular representations

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

    Follows a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    Stinger reminds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     averaged
    -0.57
     jarang
    -0.56
    withOpacity
    -0.56
     jurí
    -0.56
     meines
    -0.56
     jurídica
    -0.55
     Regel
    -0.55
    -0.55
    didSet
    -0.54
    UseVisualStyle
    -0.54
    POSITIVE LOGITS
     Meanwhile
    0.65
     convinces
    0.59
    Meanwhile
    0.59
     realizes
    0.58
     angrily
    0.57
     pretending
    0.57
     meanwhile
    0.55
     realizing
    0.55
     revealed
    0.54
     convinced
    0.52
    Act Density 0.275%

    No Known Activations