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

    Neuronpedia

    INDEX
    Explanations

    function prototypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    1.32
    ות
    1.22
    ні
    1.20
    ின்
    1.20
    ing
    1.16
    ти
    1.13
    רי
    1.09
    ί
    1.07
    og
    1.05
    кт
    1.04
    POSITIVE LOGITS
    ال
    1.47
    ه
    1.40
    N
    1.34
    ne
    1.29
    ب
    1.29
    S
    1.28
    F
    1.23
    L
    1.16
    cción
    1.09
    D
    1.09
    Act Density 0.000%

    No Known Activations