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

    Neuronpedia

    INDEX
    Explanations

    contrace

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    push
    -0.08
    _PARAMETERS
    -0.07
     por
    -0.07
     Delicious
    -0.07
     feder
    -0.07
    Pool
    -0.06
    arehouse
    -0.06
    іту
    -0.06
    _mar
    -0.06
    _logs
    -0.06
    POSITIVE LOGITS
    .Authorization
    0.07
     maternal
    0.06
    .Option
    0.06
     활
    0.06
    [field
    0.06
    (Route
    0.06
    anche
    0.06
    .fb
    0.06
    justice
    0.06
     修
    0.06
    Act Density 0.002%

    No Known Activations