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

    Neuronpedia

    INDEX
    Explanations

    introducing explanations and evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ようで
    0.50
    かもしれませんが
    0.46
    कायदा
    0.45
     allerlei
    0.44
     insanların
    0.44
     نحاول
    0.43
    នុស្ស
    0.43
    ዝና
    0.43
     মানুষদের
    0.42
    度和
    0.42
    POSITIVE LOGITS
    ↵
    0.51
    ↵↵
    0.47
     )
    0.45
    .)
    0.45
    ).
    0.44
    <unused2172>
    0.44
    ė
    0.43
    .
    0.42
    <unused2126>
    0.42
    ک
    0.42
    Act Density 0.336%

    No Known Activations