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

    Neuronpedia

    INDEX
    Explanations

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اسم
    -0.07
    ué
    -0.06
    /provider
    -0.06
     又
    -0.06
    ideos
    -0.06
    ‌توان
    -0.06
    eco
    -0.06
    �
    -0.06
    _tweets
    -0.06
    -res
    -0.06
    POSITIVE LOGITS
    (Math
    0.09
    /Math
    0.08
     Math
    0.08
    Carbon
    0.07
    =Math
    0.07
     alınması
    0.07
    atively
    0.07
    Λ
    0.07
    =req
    0.06
    [Math
    0.06
    Act Density 0.002%

    No Known Activations