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

    Neuronpedia

    INDEX
    Explanations

    net

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    planation
    -0.07
     André
    -0.07
    风险
    -0.06
     shy
    -0.06
     vill
    -0.06
    _br
    -0.06
     influenza
    -0.06
    ffffff
    -0.06
     tj
    -0.06
    ีซ
    -0.06
    POSITIVE LOGITS
     Net
    0.09
     net
    0.08
    Net
    0.07
     제작
    0.07
     publi
    0.07
    .Grid
    0.07
    mentor
    0.07
     threadIdx
    0.06
    GV
    0.06
    deps
    0.06
    Act Density 0.001%

    No Known Activations