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

    Neuronpedia

    INDEX
    Explanations

    occurrences of hyphenated terms and specific phonetic patterns

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

    French place names and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sünde
    -0.61
     istrinya
    -0.60
     adesivos
    -0.59
     propOrder
    -0.59
     pingente
    -0.58
     enfans
    -0.57
     vôtre
    -0.56
    Datuak
    -0.56
     sumpay
    -0.56
    horabuena
    -0.56
    POSITIVE LOGITS
    -
    0.56
    ‐
    0.38
     Hartley
    0.36
     close
    0.35
     hub
    0.35
    LookAnd
    0.35
    enumi
    0.34
    <em>
    0.34
     founding
    0.34
     correspondent
    0.34
    Act Density 0.013%

    No Known Activations