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

    Neuronpedia

    INDEX
    Explanations

    ondo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hệ
    -0.07
    �回
    -0.07
    不平衡
    -0.07
    zon
    -0.07
    流
    -0.07
    هب
    -0.07
     yyyy
    -0.06
    @Path
    -0.06
    딕
    -0.06
    混凝土
    -0.06
    POSITIVE LOGITS
    ){↵↵
    0.07
    iforn
    0.07
    ⁍
    0.07
     newPos
    0.06
     Jan
    0.06
    _handles
    0.06
    榃
    0.06
     квартир
    0.06
    illiseconds
    0.06
     которым
    0.06
    Act Density 0.002%

    No Known Activations