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

    Neuronpedia

    INDEX
    Explanations

    code snippets or programming syntax.

    oai_token-act-pair · gemini-2.0-flash

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.57
    PerformLayout
    -0.52
    رشف
    -0.48
     oprot
    -0.44
    ftagPool
    -0.43
    empêcher
    -0.40
     actifs
    -0.40
     ugu
    -0.38
    WebServlet
    -0.37
    SharedCtor
    -0.37
    POSITIVE LOGITS
     виправивши
    0.63
    SOUNDBITE
    0.61
     setObject
    0.60
    Tikang
    0.60
    oudou
    0.59
    ')")
    0.57
     مشين
    0.57
    iformis
    0.56
     endfor
    0.55
    []
    0.55
    Act Density 3.644%

    No Known Activations