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

    Neuronpedia

    INDEX
    Explanations

    plural nouns followed by code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一
    1.59
    of
    1.36
     an
    1.33
    ER
    1.29
    ED
    1.28
    會
    1.27
     on
    1.23
     at
    1.22
    RO
    1.16
    b
    1.14
    POSITIVE LOGITS
    ли
    1.83
     dimensioni
    1.48
    li
    1.43
    ла
    1.41
    يد
    1.39
    ۹
    1.38
    ת
    1.36
    ри
    1.33
    lerine
    1.33
    ない
    1.32
    Act Density 0.329%

    No Known Activations