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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Courtesy
    -0.07
    Ⲉ
    -0.07
    ᐃ
    -0.07
     под
    -0.07
    茽
    -0.06
     aligned
    -0.06
    -0.06
    �
    -0.06
    🌥
    -0.06
    指向
    -0.06
    POSITIVE LOGITS
    Atlas
    0.08
    OMETRY
    0.08
    蒸汽
    0.07
    آثار
    0.07
     двигател
    0.07
     Alpha
    0.07
    方向盘
    0.07
    昆虫
    0.07
     Yoga
    0.07
    سان
    0.07
    Act Density 0.006%

    No Known Activations