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

    Neuronpedia

    INDEX
    Explanations

    viewpoints and perspectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.80
    ،
    0.79
     are
    0.77
    i
    0.73
    ：
    0.72
    search
    0.70
    ，
    0.68
     as
    0.64
    res
    0.63
    ۹
    0.63
    POSITIVE LOGITS
    <0x80>
    0.68
    મ
    0.65
    '
    0.63
    )
    0.61
     viewpoint
    0.61
     POV
    0.59
    ம்
    0.57
     viewpoints
    0.55
     Repub
    0.54
     publiques
    0.54
    Act Density 0.015%

    No Known Activations