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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and expressions

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

    Numbers involving multiplication or exponents

    np_acts-logits-general · gemini-2.0-flash

    numbers and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OrNil
    -0.73
     certification
    -0.66
    gående
    -0.63
    Certification
    -0.62
    certification
    -0.62
     cert
    -0.61
     Certification
    -0.61
     Cer
    -0.61
    Hochspringen
    -0.61
     cer
    -0.61
    POSITIVE LOGITS
    Fifteen
    0.64
    fif
    0.63
     fifteen
    0.58
     Fifteen
    0.56
     profile
    0.54
     profiles
    0.53
    diğinde
    0.53
    onghi
    0.51
     fifteenth
    0.50
     Profile
    0.49
    Act Density 0.335%

    No Known Activations