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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сут
    -0.07
     surg
    -0.07
    _secs
    -0.07
    azines
    -0.07
     순
    -0.07
     toc
    -0.07
     vac
    -0.07
    _SECRET
    -0.06
    idential
    -0.06
    thenReturn
    -0.06
    POSITIVE LOGITS
    estate
    0.07
    רוץ
    0.06
     decrease
    0.06
    狡
    0.06
     também
    0.06
    פרופיל
    0.06
    𝕕
    0.06
     Adjustment
    0.06
    不由得
    0.06
     joking
    0.06
    Act Density 0.004%

    No Known Activations