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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and expressions in equations

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

    math expressions containing integrals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.77
    posedge
    -0.67
     للمعارف
    -0.63
    AndEndTag
    -0.62
     queſto
    -0.60
     itemView
    -0.60
     zwiſchen
    -0.60
    <unused55>
    -0.59
    <unused21>
    -0.59
    <unused47>
    -0.59
    POSITIVE LOGITS
    }+
    0.40
     незавершена
    0.39
     encima
    0.39
    yarnpkg
    0.37
     além
    0.35
    }+\
    0.35
     pérdida
    0.35
    |+\
    0.34
    }}+\
    0.33
     utilización
    0.32
    Act Density 0.299%

    No Known Activations