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

    Neuronpedia

    INDEX
    Explanations

    headers, names, or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     마
    0.46
    のマ
    0.45
     unfairly
    0.43
     マイ
    0.43
     нати
    0.43
     Kaplan
    0.43
     خم
    0.43
     सैफ
    0.42
     dismissed
    0.42
    FRS
    0.42
    POSITIVE LOGITS
     fisica
    0.46
    渐
    0.46
    changing
    0.46
    并发
    0.46
    suffix
    0.45
     futura
    0.44
     especies
    0.44
    تم
    0.44
    tint
    0.43
    امت
    0.43
    Act Density 0.001%

    No Known Activations