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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     formul
    -0.07
     WHITE
    -0.07
     kommen
    -0.06
     fly
    -0.06
    letion
    -0.06
     echoed
    -0.06
    stå
    -0.06
    _initialized
    -0.06
     entwick
    -0.06
     nickel
    -0.06
    POSITIVE LOGITS
    Doctors
    0.07
    _MATRIX
    0.06
     tidak
    0.06
    醴
    0.06
    ेर
    0.06
    ffi
    0.06
    (info
    0.06
     Payments
    0.06
     korun
    0.06
     звіт
    0.06
    Act Density 0.010%

    No Known Activations