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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships among like-minded individuals

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

    similarity and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     claims
    -0.33
    claims
    -0.33
     defendant
    -0.33
     claim
    -0.32
     reclama
    -0.31
    claim
    -0.31
     the
    -0.31
     sug
    -0.31
    ApiProperty
    -0.30
     suger
    -0.30
    POSITIVE LOGITS
    WriteBarrier
    0.70
     الحره
    0.68
    évaluateur
    0.59
     transférez
    0.58
     autorytatywna
    0.57
     kindred
    0.55
    BASELINE
    0.55
    Similar
    0.55
    RectangleBorder
    0.55
     Similar
    0.53
    Act Density 0.018%

    No Known Activations