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

    Neuronpedia

    INDEX
    Explanations

    GPL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    设计
    -0.07
     Costume
    -0.07
    ника
    -0.07
     descendants
    -0.07
    -ring
    -0.07
    Adam
    -0.06
     cần
    -0.06
    soles
    -0.06
     اند
    -0.06
    .Priority
    -0.06
    POSITIVE LOGITS
     gov
    0.06
     ओर
    0.06
    ğan
    0.06
     вор
    0.06
    -president
    0.06
     STDMETHOD
    0.06
     قانون
    0.06
     علمی
    0.06
     глав
    0.06
     třeba
    0.06
    Act Density 0.002%

    No Known Activations