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

    Neuronpedia

    INDEX
    Explanations

    potential consequences or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ונ
    1.78
    iya
    1.72
    ം
    1.71
    bling
    1.70
    べく
    1.69
     نص
    1.69
     niew
    1.66
     flicks
    1.60
     flat
    1.57
     må
    1.56
    POSITIVE LOGITS
     conceivably
    2.12
    ことになる
    2.06
    śmy
    1.92
    お店
    1.69
     eradicate
    1.69
     दर्जन
    1.65
    𝓉
    1.64
    \|
    1.63
    в
    1.61
    vict
    1.60
    Act Density 0.082%

    No Known Activations