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

    Neuronpedia

    INDEX
    Explanations

    driving, boundaries, illegal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     以及
    0.38
    以及
    0.34
    এবং
    0.30
    their
    0.29
    params
    0.29
    AND
    0.29
    F
    0.29
     AND
    0.28
     sfr
    0.28
    所
    0.28
    POSITIVE LOGITS
    ilien
    0.31
    ње
    0.30
    <unused2040>
    0.30
     histoires
    0.30
    と呼ばれる
    0.29
    Ì
    0.28
     veritable
    0.28
    Series
    0.28
    лії
    0.28
     chronicles
    0.28
    Act Density 0.333%

    No Known Activations