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

    Neuronpedia

    INDEX
    Explanations

    email drafts for actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    गुड
    0.47
    וד
    0.44
    As
    0.43
    Deep
    0.42
    ד
    0.42
    ใช้
    0.41
     และ
    0.41
    Digits
    0.41
    לה
    0.41
    גי
    0.40
    POSITIVE LOGITS
    chrane
    0.50
     filmes
    0.49
    daar
    0.46
     ú
    0.46
    stopping
    0.45
     enda
    0.45
    加载
    0.44
     shootings
    0.44
     fó
    0.44
     resets
    0.44
    Act Density 0.003%

    No Known Activations