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

    Neuronpedia

    INDEX
    Explanations

    programming libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     William
    -0.08
     Ow
    -0.07
     IPPROTO
    -0.07
     Natal
    -0.07
    =b
    -0.07
    _jwt
    -0.07
     губ
    -0.06
     pozor
    -0.06
    openhagen
    -0.06
    찮
    -0.06
    POSITIVE LOGITS
    Segment
    0.07
     brother
    0.06
    oute
    0.06
     legislation
    0.06
    Voice
    0.06
     errors
    0.06
     Prices
    0.06
    Refer
    0.06
     cort
    0.06
    _masks
    0.06
    Act Density 0.002%

    No Known Activations