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

    Neuronpedia

    INDEX
    Explanations

    tokens related to numerical values and identifiers

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

    Text fragments with non-English alphabets

    np_acts-logits-general · gemini-2.0-flash

    iohexol, venopril, scientific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.66
    bership
    -0.62
     للمعارف
    -0.61
    astéroïdes
    -0.61
    VolleyError
    -0.60
    المراجع
    -0.58
    Synonymes
    -0.57
     Chwiliwch
    -0.57
     виправивши
    -0.57
    entration
    -0.57
    POSITIVE LOGITS
     auffi
    0.58
    Autoritní
    0.54
     venuto
    0.53
     nœ
    0.49
     caufe
    0.48
    ñora
    0.47
     $_"
    0.46
    mergeFrom
    0.46
     cauſe
    0.46
     colpa
    0.46
    Act Density 0.167%

    No Known Activations