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

    Neuronpedia

    INDEX
    Explanations

    times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eşit
    -0.07
     مشاركة
    -0.07
     身
    -0.06
     raining
    -0.06
    _annotation
    -0.06
     affidavit
    -0.06
     ambigu
    -0.06
    ...
↵
    -0.06
    portlet
    -0.06
     قابلیت
    -0.06
    POSITIVE LOGITS
     completing
    0.07
    _proba
    0.06
    Bytes
    0.06
     ","
    0.06
     replacement
    0.06
     roman
    0.06
     eleg
    0.06
    _goal
    0.06
     auctions
    0.06
     Est
    0.06
    Act Density 0.000%

    No Known Activations