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

    Neuronpedia

    INDEX
    Explanations

    double

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Як
    -0.07
    COVERY
    -0.06
    説明
    -0.06
    -0.06
    markup
    -0.06
    алення
    -0.06
     antiqu
    -0.06
     sé
    -0.06
    allis
    -0.05
    severity
    -0.05
    POSITIVE LOGITS
    dives
    0.08
    .It
    0.07
    *****/↵
    0.07
    Tonight
    0.07
     "}\
    0.07
    EventType
    0.07
    ObjectType
    0.06
    .Split
    0.06
    atır
    0.06
     Pistons
    0.06
    Act Density 0.002%

    No Known Activations