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

    Neuronpedia

    INDEX
    Explanations

    temporary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gave
    -0.07
    muş
    -0.07
    酥
    -0.07
    陷
    -0.07
    .GraphicsUnit
    -0.07
    黥
    -0.07
    出
    -0.07
     cual
    -0.07
    耜
    -0.07
     podr
    -0.07
    POSITIVE LOGITS
    /max
    0.08
    計
    0.08
     Alarm
    0.07
    英雄
    0.07
     marching
    0.07
    봊
    0.07
     Fall
    0.07
    Constraint
    0.07
    	Collection
    0.07
     Thời
    0.06
    Act Density 0.032%

    No Known Activations