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

    Neuronpedia

    INDEX
    Explanations

    seemingly random character sequences and fragments of words, possibly indicating a corrupted or poorly formatted text

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noDo
    -0.52
    <>("
    -0.47
    <?=
    -0.47
    Hochspringen
    -0.47
     H
    -0.46
    انيف
    -0.45
     Exactos
    -0.44
     
    -0.44
     C
    -0.44
     G
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.84
     fubject
    0.76
    存于互联网档案馆
    0.71
     colère
    0.70
    ագրություններ
    0.67
     rootReducer
    0.66
     faſt
    0.64
     Monfieur
    0.63
    Betyg
    0.62
     ―――――
    0.62
    Act Density 0.997%

    No Known Activations