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

    Neuronpedia

    INDEX
    Explanations

    hair length and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    1.21
    fer
    1.16
    о
    1.14
    fl
    1.10
    ter
    1.09
    al
    1.05
    х
    1.04
    per
    1.00
    an
    0.98
    py
    0.98
    POSITIVE LOGITS
    َى
    1.13
    utacji
    1.05
    Ⴌ
    1.05
     ලෙස
    1.04
    至于
    1.02
    )%>%
    1.00
     tộc
    0.99
     êtes
    0.99
    쭌
    0.98
    处于
    0.97
    Act Density 0.001%

    No Known Activations