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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships or operations

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

    Followed by numbers or dates

    np_acts-logits-general · gemini-2.0-flash

    dates and times with separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    -0.98
    2
    -0.92
    3
    -0.89
    0
    -0.86
    5
    -0.83
    4
    -0.83
    6
    -0.80
    7
    -0.80
    9
    -0.78
    8
    -0.73
    POSITIVE LOGITS
    httphttps
    0.63
     useAuth
    0.62
    ագրություններ
    0.61
    íncia
    0.61
     useParams
    0.56
    tabak
    0.54
     surla
    0.53
    sidemargin
    0.52
     Himo
    0.51
    ulite
    0.51
    Act Density 0.339%

    No Known Activations