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

    Neuronpedia

    INDEX
    Explanations

    CPU features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?',
    -0.08
     opinions
    -0.07
    minated
    -0.07
    itting
    -0.06
    Legal
    -0.06
     drowned
    -0.06
    MY
    -0.06
     نزدیک
    -0.06
    staff
    -0.06
     decreasing
    -0.06
    POSITIVE LOGITS
    //================================================
    0.07
    ００
    0.06
    زو
    0.06
    _Form
    0.06
     Broadcom
    0.06
    士
    0.06
     keywords
    0.06
    σμ
    0.06
    리를
    0.06
    腐
    0.06
    Act Density 0.010%

    No Known Activations