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

    Neuronpedia

    INDEX
    Explanations

    fairly followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     restantes
    2.09
    骓
    1.90
     конечно
    1.85
     suivantes
    1.84
    COMPILE
    1.84
    <unused23>
    1.83
     viêm
    1.81
    agamanam
    1.80
     suivants
    1.80
     habituellement
    1.80
    POSITIVE LOGITS
    ك
    2.45
    ח
    2.16
    א
    2.13
    or
    1.98
    ang
    1.81
    one
    1.78
    ่
    1.78
    ich
    1.77
    ong
    1.76
    ened
    1.76
    Act Density 0.027%

    No Known Activations