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

    Neuronpedia

    INDEX
    Explanations

    access to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.63
    О
    0.53
     борьбе
    0.51
    ghar
    0.48
     Оно
    0.48
    كي
    0.47
    uintes
    0.47
    ku
    0.47
     Необходимо
    0.46
    Geschichte
    0.46
    POSITIVE LOGITS
     access
    0.92
     доступа
    0.90
     toegang
    0.84
     Access
    0.80
     accès
    0.79
     accessing
    0.77
     acesso
    0.77
     acceder
    0.76
     acessar
    0.74
     mengakses
    0.71
    Act Density 1.058%

    No Known Activations