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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .")↵
    -0.07
    Na
    -0.07
    www
    -0.07
     �
    -0.06
    _sem
    -0.06
     alien
    -0.06
    洭
    -0.06
    �
    -0.06
    キ
    -0.06
    queryString
    -0.06
    POSITIVE LOGITS
     Representatives
    0.08
     Seymour
    0.07
     الاول
    0.07
     Moderator
    0.07
    เอกสาร
    0.07
    _ORD
    0.07
     convent
    0.07
     clinicians
    0.07
    音樂
    0.07
     tutti
    0.07
    Act Density 0.047%

    No Known Activations