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

    Neuronpedia

    INDEX
    Explanations

    words starting with Ac

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    3.14
    entropy
    2.86
    hearted
    2.77
     elucidate
    2.77
    ל
    2.76
    currentPlayer
    2.74
    이
    2.72
    実際
    2.67
     legen
    2.66
     aromatic
    2.62
    POSITIVE LOGITS
    িকাংশ
    3.18
    邬
    2.97
     mää
    2.83
    MACl
    2.76
    ن
    2.76
     thaliana
    2.76
    dote
    2.70
    rš
    2.65
    िक
    2.63
    ance
    2.58
    Act Density 0.142%

    No Known Activations