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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    основ
    -0.07
     чим
    -0.06
    .bc
    -0.06
    *out
    -0.06
    แป
    -0.06
    íd
    -0.06
    様
    -0.06
    무
    -0.06
     toute
    -0.06
    hour
    -0.06
    POSITIVE LOGITS
     Figure
    0.07
     milestones
    0.06
     $↵↵
    0.06
     во
    0.06
    Train
    0.06
     ren
    0.06
     Figures
    0.06
     ;↵↵↵
    0.06
    Nickname
    0.06
    START
    0.06
    Act Density 0.184%

    No Known Activations