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

    Neuronpedia

    INDEX
    Explanations

    saturation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Execution
    -0.07
     Thumbnails
    -0.07
    \xb
    -0.07
    cee
    -0.07
    TextArea
    -0.07
    (operator
    -0.06
     fseek
    -0.06
    ollections
    -0.06
    _PM
    -0.06
    enha
    -0.06
    POSITIVE LOGITS
    olph
    0.06
    ONUS
    0.06
    eff
    0.06
    acja
    0.06
    .stereotype
    0.06
    тоф
    0.06
    olio
    0.06
    ');↵↵↵
    0.06
     Doğ
    0.06
     harms
    0.06
    Act Density 0.005%

    No Known Activations