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

    Neuronpedia

    INDEX
    Explanations

    Stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getDeclared
    -0.07
    $conn
    -0.07
    Sch
    -0.06
    牯
    -0.06
    >↵↵↵
    -0.06
    elix
    -0.06
    _CHECK
    -0.06
     jov
    -0.06
     Ricky
    -0.06
     loader
    -0.06
    POSITIVE LOGITS
    .Extension
    0.09
    .ms
    0.08
    睁开
    0.07
     الأو
    0.07
    ]("
    0.07
     qa
    0.07
     Shed
    0.07
    ceptors
    0.07
    asl
    0.07
    atsu
    0.07
    Act Density 0.001%

    No Known Activations