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

    Neuronpedia

    INDEX
    Explanations

    wrapper(*args, **kwargs)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     today
    0.45
    Today
    0.44
    स्
    0.40
     Edgar
    0.39
    Humidity
    0.38
    ቛ
    0.38
    积
    0.38
     saying
    0.38
    𝗦
    0.38
    drá
    0.37
    POSITIVE LOGITS
     казіно
    0.40
     ਹ
    0.40
     svar
    0.39
     インテリア
    0.39
    udades
    0.38
     カーボン
    0.37
     k
    0.36
    bfc
    0.36
     म्हटले
    0.36
     لا
    0.35
    Act Density 0.000%

    No Known Activations