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

    Neuronpedia

    INDEX
    Explanations

    special formatting characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ri
    0.45
    ’
    0.41
    ts
    0.32
    ри
    0.31
     APIs
    0.31
    u
    0.31
    li
    0.30
    ول
    0.30
    ugan
    0.29
    arnas
    0.29
    POSITIVE LOGITS
    ה
    0.39
     pierwszy
    0.34
    H
    0.34
    The
    0.34
    Not
    0.34
    ่
    0.33
     The
    0.33
     jokingly
    0.33
    고
    0.33
    仅
    0.33
    Act Density 3.077%

    No Known Activations