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

    Neuronpedia

    INDEX
    Explanations

    latex author block \\ UNIVERSITY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    讓你
    0.38
    Hval
    0.36
    …).
    0.35
     नाइट्र
    0.35
    Stranger
    0.35
    醣
    0.34
     божомол
    0.34
     patios
    0.34
    让你
    0.34
    ച്ചത്
    0.34
    POSITIVE LOGITS
    *,
    0.62
    †
    0.61
     $^{
    0.55
     *,
    0.55
    ∗
    0.55
     ${
    0.54
    ,*
    0.53
    *}
    0.52
     PhD
    0.52
    orcid
    0.52
    Act Density 0.001%

    No Known Activations