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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     influence
    -0.07
    疲
    -0.06
     Mara
    -0.06
     destac
    -0.06
     fault
    -0.06
     Mariners
    -0.06
     jobs
    -0.06
    .quit
    -0.06
     hockey
    -0.06
     variants
    -0.06
    POSITIVE LOGITS
     mid
    0.07
     Positioned
    0.06
     सकत
    0.06
     UITableView
    0.06
    ΙΟΥ
    0.06
    //=
    0.06
     <!
    0.06
     aggrav
    0.06
    <>↵
    0.06
     Afghanistan
    0.06
    Act Density 0.005%

    No Known Activations