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

    Neuronpedia

    INDEX
    Explanations

    sentence endings and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     covariates
    0.42
     cô
    0.42
     cheerio
    0.40
     endowments
    0.40
     entitlements
    0.40
     loadings
    0.39
     impedances
    0.39
     非
    0.39
     einf
    0.39
     corroborate
    0.39
    POSITIVE LOGITS
    al
    0.46
    adne
    0.45
    est
    0.45
    irst
    0.43
    ana
    0.43
    வண
    0.42
    html
    0.41
    R
    0.41
    वाह
    0.41
    ğın
    0.41
    Act Density 0.001%

    No Known Activations