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

    Neuronpedia

    INDEX
    Explanations

    array structures or data types in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    form input keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tebal
    -0.35
     grueso
    -0.35
     abbond
    -0.32
     Expédié
    -0.32
     again
    -0.32
    abord
    -0.31
     térmico
    -0.30
     plupart
    -0.30
     scuro
    -0.30
     AGAIN
    -0.30
    POSITIVE LOGITS
    ['
    0.77
     StatefulWidget
    0.65
    Jeografia
    0.62
     $_[
    0.62
    OGND
    0.60
    ::_('
    0.59
     BoxFit
    0.57
    specialchars
    0.56
    ########.
    0.55
    KommentareTeilen
    0.54
    Act Density 0.002%

    No Known Activations