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

    Neuronpedia

    INDEX
    Explanations

    brackets and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ريس
    -0.07
     puis
    -0.07
     secluded
    -0.06
    τολ
    -0.06
    เกาะ
    -0.06
     kendi
    -0.06
     rumors
    -0.06
     showMessage
    -0.06
    عنوان
    -0.06
    Bel
    -0.06
    POSITIVE LOGITS
     vaccinations
    0.08
     отверсти
    0.07
     Abb
    0.06
    SPEC
    0.06
    .nome
    0.06
    "],["
    0.06
    :black
    0.06
    outfile
    0.06
     responsibly
    0.06
     Nurs
    0.06
    Act Density 0.119%

    No Known Activations