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

    Neuronpedia

    INDEX
    Explanations

    or dial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     R
    0.46
    泂
    0.44
    R
    0.43
     Ol
    0.42
    อิน
    0.40
     md
    0.38
     Mad
    0.38
     Mah
    0.37
     reliable
    0.36
     rosin
    0.35
    POSITIVE LOGITS
     PU
    0.39
    pu
    0.39
    Пу
    0.38
    プリング
    0.37
     الظ
    0.37
    ण्डा
    0.36
    TextViewStyle
    0.36
    ﮨ
    0.36
    Pu
    0.35
    Lady
    0.35
    Act Density 0.009%

    No Known Activations