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

    Neuronpedia

    INDEX
    Explanations

    specific mathematical notation or symbols used in equations

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

    closing parentheses followed by technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inscrivez
    -0.71
     ainfi
    -0.66
     feroit
    -0.66
     avoient
    -0.64
     vœ
    -0.62
     pouvoit
    -0.62
     plufieurs
    -0.60
     auroit
    -0.59
     dedans
    -0.57
     Ursache
    -0.57
    POSITIVE LOGITS
    __":
    0.66
    "]
    0.65
    ']);
    0.65
    "])
    0.63
     ")
    0.63
    __':
    0.62
    ']))
    0.62
    $
    0.61
    ")));
    0.61
    "))
    0.59
    Act Density 0.150%

    No Known Activations