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

    Neuronpedia

    INDEX
    Explanations

    levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     지정
    -0.06
     brands
    -0.06
     Bro
    -0.06
    \Image
    -0.06
    ож
    -0.06
    एन
    -0.06
    /dd
    -0.06
     customers
    -0.06
    ربی
    -0.06
    移動
    -0.06
    POSITIVE LOGITS
    _finalize
    0.07
    Notes
    0.07
     Nashville
    0.07
     cush
    0.07
     nejvyšší
    0.06
     disgr
    0.06
     @}
    0.06
     tt
    0.06
     level
    0.06
    แนะนำ
    0.06
    Act Density 0.011%

    No Known Activations