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

    Neuronpedia

    INDEX
    Explanations

    graph theory/networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     satur
    -0.07
    ैं.
    -0.07
    56
    -0.06
    �
    -0.06
    race
    -0.06
     discard
    -0.06
    لل
    -0.06
    替
    -0.06
    through
    -0.06
    tractor
    -0.06
    POSITIVE LOGITS
     Ky
    0.09
    (Api
    0.07
     AlertDialog
    0.07
     suicidal
    0.07
    اغ
    0.07
    _pwm
    0.06
     phenomena
    0.06
     úspěš
    0.06
    ="{{
    0.06
     molto
    0.06
    Act Density 0.003%

    No Known Activations