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

    Neuronpedia

    INDEX
    Explanations

    dirty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //(
    -0.07
    528
    -0.07
     JT
    -0.07
    卡
    -0.06
     defensively
    -0.06
     Yoga
    -0.06
     systemd
    -0.06
     mesa
    -0.06
    ізнес
    -0.06
     EVENT
    -0.06
    POSITIVE LOGITS
     dirty
    0.09
     Dirty
    0.08
     naughty
    0.08
    dirty
    0.07
    ',{'
    0.07
    Encoding
    0.07
    _personal
    0.06
    irty
    0.06
     filthy
    0.06
    starts
    0.06
    Act Density 0.004%

    No Known Activations