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

    Neuronpedia

    INDEX
    Explanations

    depict explicit acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ብዙ
    0.53
     maail
    0.52
     جهانی
    0.51
     allez
    0.50
     ఎలా
    0.49
     hız
    0.49
     éton
    0.49
     മികച്ച
    0.48
     çarp
    0.48
    ྥ
    0.47
    POSITIVE LOGITS
     lawful
    0.64
     lawfully
    0.64
     or
    0.62
    any
    0.58
     bona
    0.57
     или
    0.57
    or
    0.56
     identifiable
    0.55
     substantially
    0.54
     reasonably
    0.54
    Act Density 0.495%

    No Known Activations