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

    Neuronpedia

    INDEX
    Explanations

    code examples and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WIDTH
    0.42
    Washington
    0.41
    if
    0.40
    l
    0.40
    va
    0.39
    MaxWidth
    0.38
     y
    0.37
     Washington
    0.37
    washington
    0.37
    idamente
    0.37
    POSITIVE LOGITS
     résultats
    0.42
     confidentialité
    0.42
     résult
    0.41
     dég
    0.41
    桶
    0.39
    ớt
    0.39
    ประสิทธิภาพ
    0.38
     substituent
    0.38
     ther
    0.37
     लिंग
    0.37
    Act Density 0.010%

    No Known Activations