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

    Neuronpedia

    INDEX
    Explanations

    establishing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    مشاركة
    -0.07
     retrieved
    -0.07
    (return
    -0.07
    SELECT
    -0.07
     Unlimited
    -0.06
     constants
    -0.06
    (Object
    -0.06
    גים
    -0.06
    chemy
    -0.06
    .GUI
    -0.06
    POSITIVE LOGITS
    钥
    0.07
     whirl
    0.07
     ')[
    0.07
    家用
    0.07
     urz
    0.07
    PlainText
    0.06
     craz
    0.06
     ITV
    0.06
     quieter
    0.06
     qc
    0.06
    Act Density 0.000%

    No Known Activations