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

    Neuronpedia

    INDEX
    Explanations

    sk your api key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MN
    0.47
    Μ
    0.46
    P
    0.45
    Wer
    0.42
     TED
    0.42
    Z
    0.42
    Hud
    0.42
    ICA
    0.41
    UED
    0.41
    AN
    0.41
    POSITIVE LOGITS
     gf
    0.49
    ริ่ม
    0.45
     sixties
    0.44
     abc
    0.43
    ष्ठी
    0.41
    েই
    0.41
    ष्णु
    0.40
     gums
    0.40
     spoons
    0.40
    팅
    0.39
    Act Density 0.002%

    No Known Activations