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

    Neuronpedia

    INDEX
    Explanations

    software copyright lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mā
    -0.90
     GameManager
    -0.84
    $$
    -0.84
     sagen
    -0.81
     betek
    -0.78
    Aprove
    -0.77
    ajemy
    -0.77
     منبع
    -0.77
     brachten
    -0.74
     primaire
    -0.73
    POSITIVE LOGITS
     getragen
    0.84
     item
    0.82
    aryng
    0.78
    gecko
    0.76
    item
    0.76
    렬
    0.75
     numbering
    0.74
     flaming
    0.74
    гиоз
    0.73
    晰
    0.71
    Act Density 0.012%

    No Known Activations