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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    畢業
    -0.07
     Certified
    -0.07
    .fullName
    -0.07
    Avg
    -0.07
    /book
    -0.07
    führer
    -0.07
    眼前
    -0.07
    usahaan
    -0.07
    )return
    -0.07
    ㎡
    -0.07
    POSITIVE LOGITS
    太空
    0.07
    ##↵
    0.07
    >;↵
    0.06
    Tok
    0.06
    ᒋ
    0.06
    Sequence
    0.06
    ع
    0.06
    调查
    0.06
    盖
    0.06
    Կ
    0.06
    Act Density 0.018%

    No Known Activations