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

    Neuronpedia

    INDEX
    Explanations

    regression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Turing
    0.42
     protocolos
    0.40
    تال
    0.39
     분포
    0.38
     Raider
    0.38
     المنت
    0.38
     Apica
    0.38
     Distributions
    0.38
     Fellows
    0.37
     denunci
    0.37
    POSITIVE LOGITS
     regression
    1.20
     regressions
    1.13
    Regression
    1.06
     Regression
    1.01
    regression
    0.95
     regress
    0.93
     regres
    0.89
     मॉडल
    0.87
     model
    0.87
     모델
    0.87
    Act Density 0.028%

    No Known Activations