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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and words indicating obligation or possibility

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

    technical and multilingual words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zijne
    -0.54
     dezelve
    -0.53
     zoude
    -0.50
     ?</
    -0.47
     للاسماء
    -0.45
     nigdy
    -0.45
    nobyl
    -0.44
     $_(
    -0.44
     MainAxisSize
    -0.44
     nodeId
    -0.44
    POSITIVE LOGITS
     Kaufman
    0.58
     Ackerman
    0.52
     Krieger
    0.51
    のり
    0.50
    Civil
    0.50
    tolist
    0.49
    ->
    0.49
     Leal
    0.48
     aimé
    0.47
     Hoffman
    0.46
    Act Density 0.007%

    No Known Activations