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

    Neuronpedia

    INDEX
    Explanations

    ol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    klär
    -0.08
     кораб
    -0.07
     juven
    -0.07
     ejected
    -0.06
     racist
    -0.06
    erer
    -0.06
    CSV
    -0.06
    etě
    -0.06
     Mercy
    -0.06
     blurred
    -0.06
    POSITIVE LOGITS
     cla
    0.07
    变得
    0.07
    パ
    0.07
     nuestra
    0.06
     svenska
    0.06
    (ws
    0.06
    _SYSTEM
    0.06
    Payments
    0.06
    /**↵
    0.06
    ):↵
    0.06
    Act Density 0.000%

    No Known Activations