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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uurd
    -0.09
     forgiveness
    -0.08
     الأ
    -0.08
    _iterations
    -0.08
     Flush
    -0.08
    Length
    -0.08
     Tons
    -0.08
    -0.07
     талант
    -0.07
    Iterations
    -0.07
    POSITIVE LOGITS
    번째
    0.10
    '",
    0.08
    '(
    0.08
     поле
    0.08
     hazard
    0.08
     번째
    0.08
     two
    0.08
    째
    0.08
    (ii
    0.07
    (?:
    0.07
    Act Density 0.337%
    No Known Activations