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

    Neuronpedia

    INDEX
    Explanations

    Δ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ՝
    -0.07
    特别
    -0.07
    惊奇
    -0.07
    肺炎
    -0.07
    ﯚ
    -0.07
    	pr
    -0.06
    /md
    -0.06
    /bootstrap
    -0.06
    יטב
    -0.06
    ubi
    -0.06
    POSITIVE LOGITS
     Δ
    0.07
     fictional
    0.07
     город
    0.07
     An
    0.07
    Disposable
    0.07
     Portsmouth
    0.07
    хват
    0.07
    国外
    0.07
     Disposable
    0.07
    (language
    0.06
    Act Density 0.001%

    No Known Activations