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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce evidence or reasoning

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

    by assumption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.84
    iſen
    -0.80
     kasarigan
    -0.79
    ſicht
    -0.77
    ſcher
    -0.77
    KommentareTeilen
    -0.77
     Akismet
    -0.76
     للاسماء
    -0.74
     informée
    -0.74
     otomatig
    -0.73
    POSITIVE LOGITS
    The
    0.45
     the
    0.43
     The
    0.35
     själva
    0.32
    .
    0.31
    Since
    0.31
     gegevens
    0.31
     wypad
    0.30
     zamanda
    0.30
    As
    0.30
    Act Density 0.044%

    No Known Activations