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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     and
    -0.08
    ,and
    -0.06
    /downloads
    -0.06
    /sc
    -0.06
     highlighting
    -0.06
     bailout
    -0.05
    )||(
    -0.05
     ThemeData
    -0.05
     nonlinear
    -0.05
    761
    -0.05
    POSITIVE LOGITS
     slot
    0.07
     té
    0.07
     Meter
    0.07
     lety
    0.06
    Cİ
    0.06
    페이지
    0.06
    _parallel
    0.06
     keto
    0.06
     Tahoe
    0.06
    .th
    0.06
    Act Density 0.065%

    No Known Activations