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

    Neuronpedia

    INDEX
    Explanations

    regression and registration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rune
    0.40
     Kxa
    0.35
    anyl
    0.35
     ئۇ
    0.35
    ඓ
    0.35
     राइड
    0.35
     bride
    0.34
    фер
    0.34
    bride
    0.34
     #-}
    0.33
    POSITIVE LOGITS
    Reg
    3.66
     reg
    3.56
     Reg
    3.53
    reg
    3.22
     regression
    3.11
    Regression
    3.03
     Regression
    3.03
     REG
    2.97
     regressions
    2.95
     Regent
    2.94
    Act Density 0.078%

    No Known Activations