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

    Neuronpedia

    INDEX
    Explanations

    instances of complex mathematical expressions and symbols

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

    mathematical formulas and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.87
    majánló
    -0.80
     Meksiku
    -0.79
     AssemblyCulture
    -0.76
     deſſen
    -0.75
    mpagne
    -0.75
     témoig
    -0.73
    <unused16>
    -0.73
    <unused14>
    -0.73
    <unused8>
    -0.73
    POSITIVE LOGITS
    ><
    0.44
     not
    0.39
    s
    0.36
     is
    0.34
    -
    0.34
    ish
    0.33
     яка
    0.31
    "><
    0.30
    ,
    0.30
    \
    0.30
    Act Density 0.047%

    No Known Activations