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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irates
    -0.08
    ीं,
    -0.07
     rob
    -0.07
     webdriver
    -0.07
     seamless
    -0.07
     hlav
    -0.07
     TextInput
    -0.06
    Consulta
    -0.06
    Yang
    -0.06
     Prostit
    -0.06
    POSITIVE LOGITS
     distorted
    0.07
    握
    0.06
     promoter
    0.06
    /config
    0.06
    .IGNORE
    0.06
    _Link
    0.06
    COVER
    0.06
    .mouse
    0.06
    .tif
    0.06
    _parameter
    0.06
    Act Density 0.043%

    No Known Activations