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

    Neuronpedia

    INDEX
    Explanations

    lecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    诚
    -0.06
     sonunda
    -0.06
     yacht
    -0.06
    _space
    -0.06
     içi
    -0.06
    ança
    -0.06
     устра
    -0.06
     "{}
    -0.06
     rusty
    -0.06
    .TIME
    -0.06
    POSITIVE LOGITS
     Countries
    0.07
     sympt
    0.07
     Discord
    0.06
    Neighbor
    0.06
    .xxx
    0.06
     Emily
    0.06
    .gallery
    0.06
    gfx
    0.06
    ulfill
    0.06
    xl
    0.06
    Act Density 0.000%

    No Known Activations