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

    Neuronpedia

    INDEX
    Explanations

    mention of prior knowledge or experience

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

    already, previously, before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fais
    -0.33
     <>",
    -0.33
     уз
    -0.33
     Eleg
    -0.32
     onPostExecute
    -0.31
    ArgsConstructor
    -0.30
    intas
    -0.30
     ус
    -0.29
     cours
    -0.28
    SYNOPSIS
    -0.28
    POSITIVE LOGITS
     EconPapers
    0.66
    abestanden
    0.61
     gynhyrchwyd
    0.61
    oredCriteria
    0.57
    хьтан
    0.57
     تكبرها
    0.56
     dezelve
    0.56
     désolés
    0.55
     الرياضيه
    0.54
    ]")]
    0.54
    Act Density 0.319%

    No Known Activations