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

    Neuronpedia

    INDEX
    Explanations

    pushing forward or through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    2.13
    ons
    1.93
    tı
    1.90
    -
    1.88
    ees
    1.79
    tia
    1.77
    czne
    1.72
    ati
    1.71
    pository
    1.65
     учета
    1.63
    POSITIVE LOGITS
    くちゃ
    2.05
    ล
    2.02
    ة
    1.96
    म
    1.86
    𝗘
    1.85
     Послед
    1.84
     इतना
    1.78
     surjective
    1.76
     fièvre
    1.73
    в
    1.70
    Act Density 0.017%

    No Known Activations