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

    Neuronpedia

    INDEX
    Explanations

    special characters and various formatting symbols used in text

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

    user followed by code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "?>
    -0.41
     strug
    -0.38
    sodik
    -0.37
     barran
    -0.37
     curso
    -0.36
     reca
    -0.35
    {};
    -0.35
    itzt
    -0.35
     Curso
    -0.34
     OFFICERS
    -0.34
    POSITIVE LOGITS
     autorytatywna
    0.60
     Wicidata
    0.56
    +#+
    0.55
    enumii
    0.55
    RegistryLite
    0.54
     boneca
    0.52
    FontStyle
    0.52
     nahilalakip
    0.52
    addGap
    0.51
     irmã
    0.50
    Act Density 0.008%

    No Known Activations