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

    Neuronpedia

    INDEX
    Explanations

    increasing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suoi
    -0.07
    وجود
    -0.07
     necesita
    -0.07
     Ortiz
    -0.07
     -↵
    -0.07
    ीप
    -0.07
    quota
    -0.07
    riminal
    -0.07
     gusta
    -0.06
     stránky
    -0.06
    POSITIVE LOGITS
    Industry
    0.07
    .Comment
    0.06
    endment
    0.06
     Token
    0.06
     Move
    0.06
     category
    0.06
    479
    0.06
    According
    0.06
    (LocalDate
    0.06
    zers
    0.06
    Act Density 0.000%

    No Known Activations