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

    Neuronpedia

    INDEX
    Explanations

    shader code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בחיים
    -0.07
     Nguyễn
    -0.07
    hyth
    -0.06
    更多精彩
    -0.06
     interventions
    -0.06
    -ready
    -0.06
    方方面面
    -0.06
    izz
    -0.06
     kicks
    -0.06
     hitters
    -0.06
    POSITIVE LOGITS
    额头
    0.08
    ها
    0.07
     Rectangle
    0.07
    _edit
    0.07
     Bay
    0.07
     text
    0.06
    bé
    0.06
    uplicate
    0.06
    ){
↵
    0.06
    缥
    0.06
    Act Density 0.006%

    No Known Activations