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

    Neuronpedia

    INDEX
    Explanations

    request related tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ר
    2.72
    й
    2.68
    ll
    2.39
    nde
    2.38
    ز
    2.33
     شریف
    2.32
    続きを読む
    2.31
    бие
    2.26
    RequestBody
    2.24
    ounced
    2.24
    POSITIVE LOGITS
     maaf
    3.18
     foremost
    3.16
    aurants
    3.05
    or
    3.04
     waveform
    2.97
    ubarb
    2.92
    اً
    2.91
     butadiene
    2.90
    eur
    2.82
    Ꭲ
    2.78
    Act Density 0.067%

    No Known Activations