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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical proofs and theorems

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

    proof of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.66
    ंदीखरीदारी
    -0.51
    styleType
    -0.50
    pulseira
    -0.50
    assic
    -0.48
     للاسماء
    -0.48
     Geſch
    -0.47
    salms
    -0.47
    Diweddarwch
    -0.47
    artifactId
    -0.47
    POSITIVE LOGITS
    Solución
    0.41
     cerve
    0.37
    Skocz
    0.37
     estima
    0.36
     correct
    0.35
     betweenstory
    0.35
    作
    0.35
     analysis
    0.35
     initially
    0.34
    Answer
    0.34
    Act Density 0.027%

    No Known Activations