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
     speak
    -0.07
     Harbour
    -0.07
    628
    -0.07
     plate
    -0.06
     journalists
    -0.06
     coding
    -0.06
     Rage
    -0.06
     حضور
    -0.06
     plates
    -0.06
     hentai
    -0.06
    POSITIVE LOGITS
    ");}↵
    0.07
    ประสบ
    0.06
    .release
    0.06
    chunks
    0.06
    Attend
    0.06
     ":"
    0.06
     laz
    0.06
     unint
    0.06
    achi
    0.06
     ji
    0.06
    Act Density 0.008%

    No Known Activations