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

    Neuronpedia

    INDEX
    Explanations

    using colormaps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RE
    1.48
    1.44
    )=$
    1.44
    ContentLoaded
    1.41
    hearted
    1.39
    স
    1.39
    &$
    1.38
     высота
    1.31
    ான்
    1.30
     accur
    1.30
    POSITIVE LOGITS
     się
    1.60
    िको
    1.56
    แหน
    1.56
    koľ
    1.54
    aż
    1.53
    აზ
    1.52
     precincts
    1.52
     fraudulently
    1.50
    뿌
    1.49
    ñones
    1.47
    Act Density 0.001%

    No Known Activations