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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卡
    -0.07
     links
    -0.07
     Applicant
    -0.06
     distressed
    -0.06
     методи
    -0.06
    _rep
    -0.06
    .getClass
    -0.06
    ً
    -0.06
    CLOCKS
    -0.06
     Cookies
    -0.06
    POSITIVE LOGITS
     result
    0.06
    -NLS
    0.06
     Pradesh
    0.06
     }
↵
↵
↵
    0.06
     경찰
    0.06
     HttpResponse
    0.06
     Deniz
    0.06
    perl
    0.06
    озя
    0.06
     Fuji
    0.06
    Act Density 0.069%

    No Known Activations