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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    妁
    -0.08
    .From
    -0.07
    纸上
    -0.07
    ruptions
    -0.07
    Ữ
    -0.06
    arking
    -0.06
     Türk
    -0.06
    PAGE
    -0.06
     رب
    -0.06
     setType
    -0.06
    POSITIVE LOGITS
     scattering
    0.07
    	console
    0.07
     infra
    0.07
     בעזר
    0.07
     invited
    0.06
     competence
    0.06
    ?!↵↵
    0.06
    yı
    0.06
    مدار
    0.06
    acent
    0.06
    Act Density 0.087%

    No Known Activations