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

    Neuronpedia

    INDEX
    Explanations

    code explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     пожи
    0.37
    ulfate
    0.35
    ဖွဲ့
    0.35
    зне
    0.33
    ἕ
    0.33
    醯
    0.33
    хи
    0.33
    ൬
    0.33
     Thurman
    0.33
     washout
    0.32
    POSITIVE LOGITS
     explained
    0.43
    script
    0.41
    css
    0.40
    That
    0.39
     optimally
    0.38
     doesn
    0.38
     completely
    0.38
    方法
    0.38
     方法
    0.38
    JavaScript
    0.38
    Act Density 0.046%

    No Known Activations