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

    Neuronpedia

    INDEX
    Explanations

    code implementation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _GROUP
    -0.06
    _range
    -0.06
    -dialog
    -0.06
     Mısır
    -0.06
    ellidos
    -0.06
     मल
    -0.06
    ッカー
    -0.06
     catapult
    -0.06
     refuge
    -0.06
     đưa
    -0.05
    POSITIVE LOGITS
     Cookie
    0.07
     LNG
    0.06
     miles
    0.06
     diagnose
    0.06
     simple
    0.06
     Campus
    0.06
    мі
    0.06
    Roman
    0.06
    /she
    0.06
     toolStrip
    0.06
    Act Density 0.071%

    No Known Activations