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

    Neuronpedia

    INDEX
    Explanations

    newline character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Force
    -0.08
     Ace
    -0.07
    ให
    -0.07
    {*
    -0.07
    Ace
    -0.07
    *******
    -0.06
    _identity
    -0.06
    _adv
    -0.06
     愛
    -0.06
    graf
    -0.06
    POSITIVE LOGITS
     Omn
    0.07
    ısından
    0.07
     ν
    0.07
    037
    0.06
     Supern
    0.06
     popping
    0.06
    unexpected
    0.06
    -n
    0.06
     PN
    0.06
    anceled
    0.06
    Act Density 0.022%

    No Known Activations