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

    Neuronpedia

    INDEX
    Explanations

    thread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     점
    -0.07
     záznam
    -0.06
    .Clone
    -0.06
     Iranian
    -0.06
     Zuckerberg
    -0.06
     Ngân
    -0.06
     للت
    -0.06
    vals
    -0.06
    unci
    -0.06
     davran
    -0.06
    POSITIVE LOGITS
    орож
    0.07
     */}↵
    0.06
    翻
    0.06
    '}>↵
    0.06
     EZ
    0.06
     Grade
    0.06
     exacerb
    0.06
    ']");↵
    0.06
     ativ
    0.06
     PAN
    0.06
    Act Density 0.009%

    No Known Activations