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

    Neuronpedia

    INDEX
    Explanations

    elements related to data importation and usage in programming contexts

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

    Code-related and non-English words

    np_acts-logits-general · gemini-2.0-flash

    specific words and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bu
    -0.54
    CppMethod
    -0.54
    onese
    -0.50
     modern
    -0.49
     om
    -0.48
     co
    -0.48
     li
    -0.48
     pos
    -0.48
     Valley
    -0.47
     mer
    -0.47
    POSITIVE LOGITS
    enumi
    0.96
     للاسماء
    0.86
    InjectAttribute
    0.85
    +#+#
    0.84
     ModelExpression
    0.81
     الرياضيه
    0.75
    Przypisy
    0.75
    endphp
    0.74
     متعلقه
    0.74
     habet
    0.72
    Act Density 0.152%

    No Known Activations