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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    腸
    -0.07
    蒡
    -0.06
    ód
    -0.06
    uddle
    -0.06
     설
    -0.06
    โทร
    -0.06
    	Time
    -0.06
    ilk
    -0.06
    眨
    -0.06
    תחר
    -0.06
    POSITIVE LOGITS
    坐落
    0.07
    .findBy
    0.07
     philosophy
    0.07
     discover
    0.07
    xi
    0.07
     paintings
    0.07
     cov
    0.07
     orbital
    0.07
    .clientX
    0.06
    当地的
    0.06
    Act Density 0.003%

    No Known Activations