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

    Neuronpedia

    INDEX
    Explanations

    detox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ze
    -0.07
     Ricky
    -0.07
     slope
    -0.07
     히
    -0.07
     Ш
    -0.07
     DIST
    -0.06
    _SMALL
    -0.06
     vested
    -0.06
    Chip
    -0.06
     المش
    -0.06
    POSITIVE LOGITS
     cleansing
    0.07
     пункт
    0.07
     detox
    0.07
     cleanse
    0.07
     genomes
    0.06
     suspension
    0.06
    llum
    0.06
     sins
    0.06
    %，
    0.06
     bizarre
    0.06
    Act Density 0.002%

    No Known Activations