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

    Neuronpedia

    INDEX
    Explanations

    name and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ㅗ
    0.84
    ziehungs
    0.82
     troisième
    0.82
     quatrième
    0.80
    NUMX
    0.77
    ｗｗ
    0.75
     XNUMX
    0.74
     cinquième
    0.74
    --"
    0.74
    ๎
    0.73
    POSITIVE LOGITS
     &
    6.29
    &
    4.57
     &,
    4.11
     &/
    4.10
     &\
    3.93
    ＆
    3.65
     (&
    3.63
     &.
    3.62
    )&
    3.50
    ,&
    3.48
    Act Density 1.418%

    No Known Activations