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

    Neuronpedia

    INDEX
    Explanations

    code keywords with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amb
    0.80
     Amb
    0.75
     irrational
    0.73
     congruent
    0.72
     Be
    0.71
     stranger
    0.69
     Nana
    0.68
     crossed
    0.64
     amounting
    0.64
     Grace
    0.63
    POSITIVE LOGITS
    ._
    1.62
    ["
    1.41
    ['
    1.34
    .__
    1.29
    .
    1.28
    .[
    1.27
    ().
    1.18
    的
    1.17
    .$.
    1.16
    .(
    1.15
    Act Density 0.507%

    No Known Activations