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

    Neuronpedia

    INDEX
    Explanations

    halluc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rest
    -0.07
     Spare
    -0.07
    ByName
    -0.06
    さ
    -0.06
     manten
    -0.06
    iddles
    -0.06
    .Rendering
    -0.06
    .Hosting
    -0.06
     vegetable
    -0.06
    单
    -0.06
    POSITIVE LOGITS
     halluc
    0.14
     grop
    0.07
     lcm
    0.07
    628
    0.07
    During
    0.07
    SC
    0.07
    182
    0.07
     uc
    0.07
    (mid
    0.06
    549
    0.06
    Act Density 0.001%

    No Known Activations