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

    Neuronpedia

    INDEX
    Explanations

    definitions and glossaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tokom
    -0.08
     parado
    -0.07
     seasons
    -0.07
     dl
    -0.07
    ушка
    -0.07
     சக
    -0.07
    uidor
    -0.07
     scoop
    -0.07
     iji
    -0.07
     strategically
    -0.07
    POSITIVE LOGITS
     pertaining
    0.15
     pertains
    0.12
     betrekking
    0.12
     betrifft
    0.12
     касается
    0.11
     concerning
    0.11
     concerne
    0.11
     cuestiones
    0.11
     αφορά
    0.10
     concerns
    0.10
    Act Density 0.027%

    No Known Activations