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

    Neuronpedia

    INDEX
    Explanations

    technical documents/information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /customer
    -0.07
     bureaucratic
    -0.07
     jet
    -0.07
    -forward
    -0.07
    -operation
    -0.06
     hanging
    -0.06
    Vir
    -0.06
    -red
    -0.06
    歡
    -0.06
    (cursor
    -0.06
    POSITIVE LOGITS
    shine
    0.07
    gon
    0.07
    malloc
    0.06
     џ
    0.06
    _HOOK
    0.06
    (radius
    0.06
    iesta
    0.06
     друго
    0.06
    gart
    0.06
    atonin
    0.06
    Act Density 0.015%

    No Known Activations