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

    Neuronpedia

    INDEX
    Explanations

    along the way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     লেখার
    0.61
     cambiar
    0.57
     INEC
    0.57
     flexible
    0.55
     dividing
    0.55
     animal
    0.54
     NOI
    0.54
     rotational
    0.53
     associative
    0.53
     Noël
    0.53
    POSITIVE LOGITS
    ।
    0.81
    ש
    0.80
    up
    0.77
    AK
    0.76
    ado
    0.76
    i
    0.75
    ente
    0.74
    re
    0.74
    w
    0.73
    kan
    0.71
    Act Density 0.000%

    No Known Activations