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

    Neuronpedia

    INDEX
    Explanations

    ellipses and other forms of whitespace formatting

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

    X11 library paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     épaules
    -0.39
    Formazione
    -0.39
     öld
    -0.31
    Moneda
    -0.28
    tralight
    -0.28
    løs
    -0.28
     sementes
    -0.28
     pères
    -0.27
    并将
    -0.27
     oreilles
    -0.26
    POSITIVE LOGITS
    ldots
    1.31
    الحياه
    0.82
    ंदीखरीदारी
    0.79
    httphttps
    0.76
     nonUne
    0.75
    uxxxx
    0.74
    rrggbb
    0.70
    …]
    0.66
     autorytatywna
    0.65
    AndEndTag
    0.64
    Act Density 0.001%

    No Known Activations