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

    Neuronpedia

    INDEX
    Explanations

    intensifier followed by adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    केमॉन
    0.57
     moldings
    0.55
     sepen
    0.55
     sabbam
    0.54
    )[
    0.54
    ಾಂಶ
    0.54
     lineColorSpace
    0.54
     solamente
    0.53
     seguenti
    0.53
     montañas
    0.53
    POSITIVE LOGITS
    .
    0.57
    R
    0.55
     F
    0.50
    t
    0.47
    L
    0.47
    em
    0.46
     R
    0.46
    优惠
    0.46
    al
    0.45
     لكن
    0.45
    Act Density 0.009%

    No Known Activations