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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SplitOptions
    -0.07
    (plugin
    -0.07
     производ
    -0.07
     Zoom
    -0.06
     funct
    -0.06
     název
    -0.06
     Formatter
    -0.06
    uParam
    -0.06
     схем
    -0.06
     дит
    -0.06
    POSITIVE LOGITS
     consult
    0.07
    _puts
    0.07
     PER
    0.07
     rockets
    0.06
     favors
    0.06
    تز
    0.06
    angles
    0.06
     halves
    0.06
    语
    0.06
    》↵
    0.06
    Act Density 0.000%

    No Known Activations