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

    Neuronpedia

    INDEX
    Explanations

    liver disease or remedy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.21
    マ
    1.13
    ０
    1.11
    ین
    1.06
    の
    1.06
     vecinos
    1.05
    々は
    1.05
     atletas
    1.04
    ありません
    1.03
    is
    1.02
    POSITIVE LOGITS
    ↵
    1.98
    I
    1.52
    N
    1.52
    T
    1.45
    K
    1.28
    O
    1.27
    that
    1.26
    M
    1.24
     that
    1.20
    g
    1.16
    Act Density 0.002%

    No Known Activations