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

    Neuronpedia

    INDEX
    Explanations

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cantidad
    1.37
     obtener
    1.36
     获取
    1.32
     prueba
    1.31
    jumlah
    1.30
     mensaje
    1.29
     asignar
    1.28
    名稱
    1.28
     naziv
    1.27
    名称
    1.27
    POSITIVE LOGITS
    ,
    0.99
    .
    0.84
    -
    0.84
    :
    0.82
    /
    0.82
     reinforcing
    0.81
    and
    0.79
    ;
    0.79
     over
    0.79
     and
    0.77
    Act Density 0.098%

    No Known Activations