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

    Neuronpedia

    INDEX
    Explanations

    current trends and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indiqu
    0.66
    ą
    0.64
    ж
    0.63
    c
    0.58
    ں
    0.58
     venant
    0.57
    ,
    0.57
    R
    0.56
    oción
    0.55
     admisión
    0.55
    POSITIVE LOGITS
     in
    0.71
     synonymous
    0.70
     be
    0.67
     recognized
    0.61
     used
    0.60
     borne
    0.56
     worldwide
    0.55
     ∼
    0.55
     legalized
    0.55
    畬
    0.55
    Act Density 0.890%

    No Known Activations