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

    Neuronpedia

    INDEX
    Explanations

    Sec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pirit
    -0.07
     Buffalo
    -0.07
    AWN
    -0.07
    orp
    -0.06
    lett
    -0.06
    ら
    -0.06
     rtrim
    -0.06
     pal
    -0.06
    оте
    -0.06
     इसल
    -0.06
    POSITIVE LOGITS
    _ec
    0.07
    ;!
    0.06
    ],
    0.06
    >>()
    0.06
    」，
    0.06
     yield
    0.06
    артам
    0.06
     grateful
    0.06
    ={}
    0.06
    $password
    0.06
    Act Density 0.000%

    No Known Activations