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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

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

    mathematical notation variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.53
    kään
    -0.52
     dafür
    -0.51
     للمعارف
    -0.51
    ServletException
    -0.50
    ofür
    -0.49
    +:+
    -0.48
    TokenNameR
    -0.48
    transQ
    -0.48
     sumpay
    -0.47
    POSITIVE LOGITS
     u
    1.13
     U
    1.02
    U
    0.88
     Ure
    0.65
    u
    0.64
     uLocal
    0.64
     UD
    0.62
     uv
    0.61
     ui
    0.61
     UI
    0.61
    Act Density 0.082%

    No Known Activations