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

    Neuronpedia

    INDEX
    Explanations

    Quantity/nearness/intensity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .share
    -0.08
     punt
    -0.08
     pagt
    -0.08
    ining
    -0.08
     pt
    -0.08
    esto
    -0.08
    pt
    -0.07
    gebnisse
    -0.07
     Dub
    -0.07
    zte
    -0.07
    POSITIVE LOGITS
     এত
    0.12
     blatant
    0.09
     इतना
    0.09
     इतनी
    0.09
     sehingga
    0.09
     इतने
    0.09
     ώστε
    0.08
    irls
    0.08
     vacc
    0.08
    ર્ષ
    0.08
    Act Density 0.104%

    No Known Activations