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

    Neuronpedia

    INDEX
    Explanations

    complex sentences and phrases with varying structures

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

    Appears before or within mathematical or numerical expressions

    np_acts-logits-general · gemini-2.0-flash

    phylogeny and group averages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.93
     дописавши
    -0.87
    Спасылкі
    -0.77
    InputTagHelper
    -0.74
    featureID
    -0.74
     insuffisamment
    -0.73
    tonode
    -0.73
     }}"></
    -0.71
     ErrIntOverflow
    -0.70
     تانيه
    -0.69
    POSITIVE LOGITS
     catena
    0.47
     tapi
    0.45
     carottes
    0.42
     but
    0.42
     teneur
    0.41
     sanitaires
    0.41
     rych
    0.41
    ответ
    0.40
     cappuccio
    0.40
     Leighton
    0.39
    Act Density 0.740%

    No Known Activations