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

    Neuronpedia

    INDEX
    Explanations

    academic addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fuk
    -0.06
    ору
    -0.06
    Gu
    -0.06
    Rates
    -0.06
    ふ
    -0.06
    قات
    -0.06
    dataset
    -0.06
    판
    -0.06
    FF
    -0.06
    Unt
    -0.06
    POSITIVE LOGITS
    _VALUE
    0.07
    _Mode
    0.07
    isNull
    0.06
     матері
    0.06
     бума
    0.06
    =open
    0.06
     fearless
    0.06
    (view
    0.06
    _Execute
    0.06
     Magnetic
    0.06
    Act Density 0.001%

    No Known Activations