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

    Neuronpedia

    INDEX
    Explanations

    protein in diet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ی
    2.38
    i
    2.32
    м
    2.24
    en
    2.20
    ️
    1.96
    ip
    1.88
    า
    1.84
    ar
    1.80
    at
    1.71
    a
    1.69
    POSITIVE LOGITS
    likle
    2.34
    cts
    2.31
    <unused590>
    2.19
    ctors
    2.19
    tham
    2.14
    <unused1860>
    2.13
    <unused1663>
    2.13
    InitStruct
    2.10
     gosta
    2.09
     behov
    2.08
    Act Density 0.251%

    No Known Activations