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

    Neuronpedia

    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.52
    also
    0.46
    0
    0.44
    >
    0.42
    T
    0.41
    2
    0.40
    1
    0.40
    contrib
    0.39
    M
    0.39
    H
    0.39
    POSITIVE LOGITS
    ITE
    0.46
    ORI
    0.45
    тность
    0.45
    IME
    0.44
    য়ার
    0.42
    ের
    0.42
    IRO
    0.42
    нную
    0.42
    นิด
    0.42
    禮
    0.42
    Act Density 0.139%

    No Known Activations