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

    Neuronpedia

    INDEX
    Explanations

    modification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /output
    -0.06
    wald
    -0.06
    -console
    -0.06
    fad
    -0.06
    remarks
    -0.06
    _curve
    -0.06
     Barrel
    -0.06
    -band
    -0.06
    تد
    -0.06
     центр
    -0.06
    POSITIVE LOGITS
     вида
    0.07
    wich
    0.06
    رس
    0.06
     ERROR
    0.06
     luckily
    0.06
    каз
    0.06
     '//
    0.06
     aft
    0.06
     애
    0.06
    掉
    0.06
    Act Density 0.001%

    No Known Activations