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

    Neuronpedia

    INDEX
    Explanations

    resistant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Funds
    -0.06
    otypes
    -0.06
    rove
    -0.06
     whip
    -0.06
    438
    -0.06
    leston
    -0.06
     makeover
    -0.06
     idle
    -0.06
     Linked
    -0.06
     Judgment
    -0.05
    POSITIVE LOGITS
    clusters
    0.07
     trắng
    0.07
     disgusting
    0.07
     Shiite
    0.07
    买
    0.06
     */,
    0.06
    ILLS
    0.06
    crease
    0.06
     Meter
    0.06
     şik
    0.06
    Act Density 0.195%

    No Known Activations