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

    Neuronpedia

    INDEX
    Explanations

    calculating ratios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flow
    -0.07
     asyncio
    -0.07
     Kimber
    -0.06
     Dortmund
    -0.06
    (fontSize
    -0.06
     Sür
    -0.06
     угод
    -0.06
    Jos
    -0.06
    names
    -0.06
     Ply
    -0.06
    POSITIVE LOGITS
    hled
    0.07
    σι
    0.07
     conquest
    0.07
    contri
    0.06
    0.06
     merely
    0.06
    ￣
    0.06
    DN
    0.06
    .+
    0.06
    (f
    0.06
    Act Density 0.025%

    No Known Activations