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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     руб
    -0.07
     подготов
    -0.06
    .SwingConstants
    -0.06
     عدم
    -0.06
     deceptive
    -0.06
    ンバー
    -0.06
     مخ
    -0.06
     сп
    -0.06
     کسی
    -0.06
     반
    -0.06
    POSITIVE LOGITS
    phony
    0.07
     Ruby
    0.07
     Gors
    0.06
    .COMP
    0.06
     Üniversitesi
    0.06
     Living
    0.06
     demokrat
    0.06
    \OptionsResolver
    0.06
     Ded
    0.06
     bids
    0.06
    Act Density 0.000%

    No Known Activations