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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cult
    -0.06
    (pt
    -0.06
     başladı
    -0.06
     seguridad
    -0.06
     thaimassage
    -0.06
     DD
    -0.06
    ovně
    -0.06
     Maryland
    -0.06
     Hawaiian
    -0.06
     --------
    -0.06
    POSITIVE LOGITS
    organized
    0.07
    ()</
    0.07
    Zen
    0.07
    "'
    0.07
     researchers
    0.07
    หนด
    0.06
    ."</
    0.06
    енью
    0.06
     memoir
    0.06
     hinges
    0.06
    Act Density 0.003%

    No Known Activations