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

    Neuronpedia

    INDEX
    Explanations

    ballot, initiatives, and elections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ร
    0.56
     Tüm
    0.54
    ı
    0.54
    ᓘ
    0.52
    ਰ
    0.52
     the
    0.51
    ці
    0.50
     від
    0.50
     ல
    0.49
    გილ
    0.49
    POSITIVE LOGITS
    own
    0.66
    RE
    0.65
    ANCY
    0.62
    '
    0.61
    Function
    0.59
     Function
    0.59
    amous
    0.59
     INCREASE
    0.59
    “
    0.59
    𝟎
    0.59
    Act Density 0.000%

    No Known Activations