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

    Neuronpedia

    INDEX
    Explanations

    sexually explicit content

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     syntactic
    1.09
     geographical
    1.03
     ontological
    1.02
     grammatical
    0.97
     Geographical
    0.96
     morally
    0.94
     financeiros
    0.94
     مذہبی
    0.92
     histological
    0.91
     morphological
    0.90
    POSITIVE LOGITS
     ரீ
    0.98
     açı
    0.89
     жак
    0.83
     activity
    0.80
     strife
    0.79
     significance
    0.78
     മിക
    0.77
     aspects
    0.77
    ALLY
    0.77
     integrity
    0.76
    Act Density 0.371%

    No Known Activations