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

    Neuronpedia

    INDEX
    Explanations

    area

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kh
    -0.08
    92
    -0.06
    urface
    -0.06
    Con
    -0.06
    York
    -0.06
    hosts
    -0.06
    沉
    -0.06
    .bot
    -0.06
     rob
    -0.06
    ine
    -0.06
    POSITIVE LOGITS
    内の
    0.06
    enddate
    0.06
     Ç
    0.06
     completing
    0.06
    غال
    0.06
    ро
    0.06
     actresses
    0.06
    ере
    0.06
     Εξ
    0.06
    -pe
    0.06
    Act Density 0.038%

    No Known Activations