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

    Neuronpedia

    INDEX
    Explanations

    software/academic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     città
    -0.07
     Allied
    -0.07
    倒霉
    -0.07
     أكد
    -0.07
    💹
    -0.07
    ערוץ
    -0.07
    连夜
    -0.07
    ᒃ
    -0.06
    מרת
    -0.06
    支付宝
    -0.06
    POSITIVE LOGITS
     bra
    0.07
     �
    0.07
    �
    0.07
     questionable
    0.07
    &page
    0.07
     separator
    0.07
    [name
    0.06
     كسارة
    0.06
    �
    0.06
    -mon
    0.06
    Act Density 0.278%

    No Known Activations