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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

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

    mathematical expressions involving integrals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.47
    )))))
    -0.43
    <eos>
    -0.41
    ))))
    -0.36
     simply
    -0.35
     volverá
    -0.34
    fæ
    -0.33
     flawlessly
    -0.32
     بان
    -0.32
     flawless
    -0.32
    POSITIVE LOGITS
    帖最后由
    0.81
    Personendaten
    0.73
     ſind
    0.73
     propOrder
    0.70
     Administrativna
    0.69
    httphttps
    0.68
     Italijani
    0.68
     ſever
    0.68
     يتيمه
    0.65
    afficheront
    0.63
    Act Density 0.627%

    No Known Activations