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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Serv
    -0.07
     дней
    -0.06
    西省
    -0.06
     Hok
    -0.06
     σχέ
    -0.06
    .servlet
    -0.06
     왔
    -0.06
     přátel
    -0.06
    .birth
    -0.06
    ための
    -0.06
    POSITIVE LOGITS
    ARP
    0.07
     volatile
    0.07
     tattoos
    0.06
    .caption
    0.06
     cigar
    0.06
    _strategy
    0.06
     allocating
    0.06
     //////////////////////////////////
    0.06
    _drop
    0.06
     iris
    0.06
    Act Density 0.000%

    No Known Activations