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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     поз
    -0.07
    mons
    -0.07
     fasta
    -0.07
     textbooks
    -0.06
    гал
    -0.06
     Verg
    -0.06
     boldly
    -0.06
     oper
    -0.06
     probably
    -0.06
    rolling
    -0.06
    POSITIVE LOGITS
     peně
    0.07
    iatric
    0.06
    hores
    0.06
     Sheep
    0.06
     gunmen
    0.06
    ْع
    0.06
     Shoe
    0.06
    itm
    0.06
     Crazy
    0.06
     Launcher
    0.06
    Act Density 0.003%

    No Known Activations