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

    Neuronpedia

    INDEX
    Explanations

    sections of text with high numerical values, likely relating to regulatory codes or sections in legal or scientific contexts

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

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بالإنجليزية
    -0.57
    بوابة
    -0.56
    OMEM
    -0.56
    PyExc
    -0.56
    
    -0.53
    oblo
    -0.53
    xue
    -0.53
    帖最后由
    -0.53
     CCS
    -0.52
     PCC
    -0.52
    POSITIVE LOGITS
     térm
    0.51
     chaqueta
    0.47
     jeudi
    0.47
     Defensa
    0.47
     enfans
    0.45
     Thursday
    0.45
    4
    0.44
     hasard
    0.43
    taskId
    0.42
    tangentMode
    0.42
    Act Density 0.025%

    No Known Activations