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

    Neuronpedia

    INDEX
    Explanations

    Excerpts from varied sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     уст
    -0.06
    -Owned
    -0.06
     {}),↵
    -0.06
     Paths
    -0.06
    映
    -0.06
     ------------
    -0.06
    왔
    -0.06
     grooming
    -0.06
    �은
    -0.06
     gotten
    -0.06
    POSITIVE LOGITS
    urchases
    0.07
    _actual
    0.07
     DAL
    0.06
     pri
    0.06
    landa
    0.06
    PROTO
    0.06
    combination
    0.06
     추
    0.06
    ozí
    0.06
    Soup
    0.06
    Act Density 0.000%

    No Known Activations