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

    Neuronpedia

    INDEX
    Explanations

    instances of various personal pronouns and their conjugations

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

    Non-English text

    np_acts-logits-general · gemini-2.0-flash

    foreign language initiators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assister
    -0.31
    InteropServices
    -0.30
     May
    -0.30
     and
    -0.29
     Jus
    -0.28
     &
    -0.28
    gon
    -0.27
     المعيارى
    -0.27
     along
    -0.26
     réessayer
    -0.26
    POSITIVE LOGITS
     increí
    0.76
     validamos
    0.71
     indígen
    0.70
     nonUne
    0.68
    Erreferentziak
    0.65
     الحره
    0.65
     Meksiku
    0.64
    ValueStyle
    0.63
     desmotivaciones
    0.63
     Normdatei
    0.62
    Act Density 1.113%

    No Known Activations