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

    Neuronpedia

    INDEX
    Explanations

    ~

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    됨
    -0.07
     pulls
    -0.07
     P
    -0.06
    据
    -0.06
    cor
    -0.06
     doorway
    -0.06
     clones
    -0.06
     assaulted
    -0.06
    所
    -0.06
    partment
    -0.06
    POSITIVE LOGITS
    เฮ
    0.07
     μία
    0.06
     форме
    0.06
     revital
    0.06
     Τι
    0.06
     dvě
    0.06
    HeaderInSection
    0.06
    courses
    0.06
     danych
    0.06
     الأخ
    0.06
    Act Density 0.010%

    No Known Activations