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

    Neuronpedia

    INDEX
    Explanations

    language, foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Пр
    -0.08
     aerodynamic
    -0.08
    :a
    -0.07
    -medium
    -0.07
     discrimination
    -0.07
     establecidos
    -0.07
    :h
    -0.07
     eingesetzt
    -0.07
    forma
    -0.07
    적으로
    -0.07
    POSITIVE LOGITS
     dian
    0.08
    .owl
    0.08
    .tsv
    0.07
    تي
    0.07
     Enrique
    0.07
     reminder
    0.07
     offender
    0.07
     overcome
    0.07
     tiế
    0.07
     Fren
    0.07
    Act Density 0.335%

    No Known Activations