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

    Neuronpedia

    INDEX
    Explanations

    away from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    櫳
    0.68
    ಹಾಸ
    0.66
    '];?>
    0.63
    <unused274>
    0.63
     않았
    0.61
    茷
    0.61
    㕮
    0.60
    ভিউ
    0.59
    ivals
    0.59
    воре
    0.59
    POSITIVE LOGITS
    ,
    1.24
    o
    1.05
    is
    1.03
    n
    0.98
    но
    0.98
    .
    0.86
     away
    0.86
    ing
    0.82
    j
    0.81
    t
    0.80
    Act Density 0.009%

    No Known Activations