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

    Neuronpedia

    INDEX
    Explanations

    say "ware"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ruiz
    -0.07
     Hacker
    -0.06
    ALIGN
    -0.06
     автор
    -0.06
     championship
    -0.06
    設
    -0.06
     JFK
    -0.06
     ケ
    -0.06
     Kafka
    -0.06
     fixation
    -0.06
    POSITIVE LOGITS
    _rem
    0.07
    /load
    0.06
    (dict
    0.06
     tất
    0.06
    .business
    0.06
     Ves
    0.06
    -loading
    0.06
    -collapse
    0.06
    nowledge
    0.06
     assistance
    0.06
    Act Density 0.001%

    No Known Activations