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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     untreated
    -0.07
     合
    -0.06
    ==============
    -0.06
    igos
    -0.06
     Iterate
    -0.06
    Val
    -0.06
    ===============↵
    -0.06
    qua
    -0.06
     aka
    -0.06
     specificity
    -0.06
    POSITIVE LOGITS
    έργ
    0.07
     Cock
    0.06
     pově
    0.06
    _challenge
    0.06
    ovah
    0.06
    드는
    0.06
    っても
    0.06
    ίσω
    0.06
     코로나
    0.06
     */)
    0.06
    Act Density 0.012%

    No Known Activations