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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _js
    -0.06
    ้ก
    -0.06
    Linux
    -0.06
    _offer
    -0.06
     staying
    -0.06
    istry
    -0.06
    CMS
    -0.06
     ebay
    -0.06
     İç
    -0.06
    madı
    -0.06
    POSITIVE LOGITS
     abducted
    0.07
     від
    0.06
     піз
    0.06
     Memory
    0.06
     "_
    0.06
    .writeln
    0.06
     anch
    0.06
     �
    0.06
     ys
    0.06
    {↵
    0.06
    Act Density 0.088%

    No Known Activations