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

    Neuronpedia

    INDEX
    Explanations

    instances or references to specific scenarios or examples

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

    in some cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.42
    writeByte
    -0.40
    hyperref
    -0.39
    ''');
    -0.38
    Touched
    -0.35
    verhält
    -0.35
     InputDecoration
    -0.35
    woch
    -0.35
     raised
    -0.34
    Subscribed
    -0.34
    POSITIVE LOGITS
     fometimes
    0.71
     sometimes
    0.70
    sometimes
    0.66
     quelquefois
    0.66
    jména
    0.65
     Sometimes
    0.64
     parfois
    0.63
    Sometimes
    0.60
     الرياضيه
    0.59
     иногда
    0.56
    Act Density 0.031%

    No Known Activations