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

    Neuronpedia

    INDEX
    Explanations

    plan, framework, study, paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    원은
    0.39
     govori
    0.38
    dürü
    0.37
    PageRoute
    0.36
    HTMLElement
    0.36
     diyor
    0.36
    නේ
    0.35
     egyszerű
    0.35
     වන්නේ
    0.34
     này
    0.34
    POSITIVE LOGITS
    ،
    0.33
     puns
    0.33
     різні
    0.32
     বেশকিছু
    0.31
    彊
    0.31
     जिनकी
    0.30
     ashamed
    0.30
     verbess
    0.30
     जिनका
    0.29
    ፣
    0.29
    Act Density 0.024%

    No Known Activations