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

    Neuronpedia

    INDEX
    Explanations

    more context or exploration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IC
    0.69
    AG
    0.68
    OUSE
    0.67
    ULU
    0.67
    IM
    0.66
    Think
    0.66
    AS
    0.64
     Dès
    0.64
    ER
    0.64
    EPEND
    0.64
    POSITIVE LOGITS
     iż
    0.71
    पणा
    0.67
     brack
    0.66
     stretches
    0.65
     grayish
    0.65
     unamb
    0.64
     أنها
    0.64
     \%$,
    0.64
     cations
    0.64
     conservatism
    0.63
    Act Density 0.000%

    No Known Activations