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

    Neuronpedia

    INDEX
    Explanations

    ort

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jaime
    -0.06
     Mas
    -0.06
     Patriot
    -0.06
     celery
    -0.06
     kẻ
    -0.06
    arat
    -0.06
    _Bar
    -0.06
    Allowed
    -0.06
    ()->
    -0.06
     Kristen
    -0.06
    POSITIVE LOGITS
    율
    0.07
    .Reg
    0.07
    >?
    0.06
    utral
    0.06
    UCT
    0.06
     rpt
    0.06
     vex
    0.06
    adder
    0.06
    LENGTH
    0.06
    (predictions
    0.06
    Act Density 0.001%

    No Known Activations