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

    Neuronpedia

    INDEX
    Explanations

    mathematical or numerical expressions and relationships

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

    or etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -0.56
     raiſ
    -0.53
     كومونز
    -0.51
    ſelves
    -0.51
     ſta
    -0.50
     وتسجيلات
    -0.50
     ſche
    -0.50
     myſelf
    -0.50
     increí
    -0.49
     desmotivaciones
    -0.49
    POSITIVE LOGITS
    连
    0.41
    etc
    0.39
     تف
    0.38
     تعدى
    0.38
     chiar
    0.38
     AssemblyCulture
    0.38
    even
    0.37
     třeba
    0.37
     même
    0.36
     dazu
    0.36
    Act Density 0.039%

    No Known Activations