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

    Neuronpedia

    INDEX
    Explanations

    AC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,—
    -0.07
    ايات
    -0.07
    agina
    -0.07
    etě
    -0.07
     bại
    -0.06
    !--
    -0.06
    로서
    -0.06
    LEGRO
    -0.06
    _FUNC
    -0.06
    Lit
    -0.06
    POSITIVE LOGITS
     blank
    0.07
     scaled
    0.07
     mortgage
    0.07
     minimum
    0.07
    Upper
    0.07
    업체
    0.06
     easy
    0.06
    aising
    0.06
     boosted
    0.06
     lowered
    0.06
    Act Density 0.000%

    No Known Activations