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

    Neuronpedia

    INDEX
    Explanations

    spaces for entertaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ong
    0.60
     }^{\
    0.58
     exalted
    0.58
     ofthe
    0.58
    ो
    0.58
     Á
    0.57
     Ó
    0.57
     falou
    0.56
    ro
    0.55
    ch
    0.55
    POSITIVE LOGITS
    ﯿ
    0.62
    VERTISING
    0.55
    作品
    0.54
    ক্ষণ
    0.52
    鷄
    0.52
    AF
    0.50
    SW
    0.50
    活用
    0.50
    IVING
    0.49
    Ს
    0.49
    Act Density 0.003%

    No Known Activations