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

    Neuronpedia

    INDEX
    Explanations

    filtration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    noop
    -0.07
     لب
    -0.07
    .override
    -0.07
     coop
    -0.06
     PROP
    -0.06
    تب
    -0.06
    retorno
    -0.06
    ��
    -0.06
     boobs
    -0.06
     آذ
    -0.06
    POSITIVE LOGITS
     filtration
    0.12
     Fighting
    0.07
    Distance
    0.07
    _transactions
    0.07
    src
    0.06
     unconstitutional
    0.06
     Dist
    0.06
     Perception
    0.06
     District
    0.06
     filtr
    0.06
    Act Density 0.001%

    No Known Activations