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

    Neuronpedia

    INDEX
    Explanations

    from to until

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ungannya
    1.07
    enche
    1.05
    etzungen
    1.04
    脷
    1.04
    oustache
    1.02
    ڈیا
    0.95
     strategist
    0.95
     cheque
    0.94
    lysis
    0.93
    ients
    0.91
    POSITIVE LOGITS
     hingga
    2.88
     onwards
    2.41
    부터
    2.40
     đến
    2.38
     to
    2.37
     ila
    2.35
     έως
    2.34
     sampai
    2.34
    to
    2.30
     till
    2.27
    Act Density 0.324%

    No Known Activations