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

    Neuronpedia

    INDEX
    Explanations

    Ranked-Choice Voting, Taylor series, Space Race

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     win
    0.52
     futbol
    0.52
     por
    0.49
     libido
    0.49
     blog
    0.48
     habitual
    0.47
     lunar
    0.47
     seafood
    0.47
     sute
    0.47
     hypothesized
    0.46
    POSITIVE LOGITS
    AST
    0.54
    HE
    0.51
    HLA
    0.51
    A
    0.51
    స్
    0.50
    COMPLETE
    0.50
    不要
    0.49
    આ
    0.48
    X
    0.48
    准备
    0.47
    Act Density 0.000%

    No Known Activations