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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.79
    f
    0.71
    Y
    0.68
    or
    0.67
     in
    0.67
    o
    0.67
    h
    0.66
    도
    0.62
    ও
    0.61
    ag
    0.60
    POSITIVE LOGITS
    リオ
    0.64
     Produtos
    0.61
    琯
    0.59
    Banco
    0.58
     човек
    0.58
     Балт
    0.58
     Кай
    0.57
    簍
    0.57
     respectivos
    0.56
     રાજ્ય
    0.55
    Act Density 0.003%

    No Known Activations