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

    Neuronpedia

    INDEX
    Explanations

    Code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lüğ
    -0.07
    χο
    -0.07
     decipher
    -0.07
     全
    -0.07
    催
    -0.07
    .Date
    -0.06
    เขต
    -0.06
     نسب
    -0.06
    舉
    -0.06
     minimizing
    -0.06
    POSITIVE LOGITS
     Window
    0.07
     Princess
    0.07
     nails
    0.07
     escorts
    0.07
     sola
    0.07
     Experience
    0.06
     Frozen
    0.06
     Exam
    0.06
     Ib
    0.06
     Ticket
    0.06
    Act Density 0.001%

    No Known Activations