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

    Neuronpedia

    INDEX
    Explanations

    .RunWith

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yecto
    -0.07
     місто
    -0.06
     frontier
    -0.06
    …)
    -0.06
     Acres
    -0.06
     minh
    -0.06
     ambition
    -0.06
    teří
    -0.06
    fair
    -0.06
     Salman
    -0.05
    POSITIVE LOGITS
    (vertical
    0.07
     Pal
    0.07
    τους
    0.06
    돌
    0.06
    _SHARE
    0.06
    เย
    0.06
    [G
    0.06
     pady
    0.06
    Sch
    0.06
    SSFWorkbook
    0.06
    Act Density 0.003%

    No Known Activations