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

    Neuronpedia

    INDEX
    Explanations

    Sports statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fluids
    -0.06
    woo
    -0.06
    ittal
    -0.06
    .Position
    -0.06
    uestra
    -0.06
    analy
    -0.06
    ",@"
    -0.06
    Controls
    -0.06
    few
    -0.06
    dge
    -0.06
    POSITIVE LOGITS
     東京
    0.07
    ....
    0.07
     sobě
    0.07
    $path
    0.07
    .generic
    0.07
    理论
    0.06
     paperwork
    0.06
     $(".
    0.06
     SCRIPT
    0.06
     손을
    0.06
    Act Density 0.021%

    No Known Activations