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

    Neuronpedia

    INDEX
    Explanations

    USA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ány
    -0.08
    aco
    -0.07
    .TEST
    -0.07
     Erotik
    -0.06
     nepř
    -0.06
    ném
    -0.06
     Kristen
    -0.06
    Fa
    -0.06
    nictvím
    -0.06
    Erot
    -0.06
    POSITIVE LOGITS
     시작
    0.07
    (title
    0.06
     "&#
    0.06
     empower
    0.06
     DEN
    0.06
     imágenes
    0.06
    乃
    0.06
     jejichž
    0.06
    .table
    0.06
    .Fill
    0.06
    Act Density 0.030%

    No Known Activations