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

    Neuronpedia

    INDEX
    Explanations

    Hot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Burke
    -0.08
     kendine
    -0.07
     средств
    -0.07
    358
    -0.07
    玲
    -0.07
     Grade
    -0.07
    _segments
    -0.06
    -grade
    -0.06
    青年
    -0.06
     surre
    -0.06
    POSITIVE LOGITS
     hot
    0.21
     Hot
    0.20
    Hot
    0.17
     HOT
    0.15
    -hot
    0.14
    hot
    0.13
     hottest
    0.11
     hotter
    0.10
    _hot
    0.10
     hotspot
    0.09
    Act Density 0.010%

    No Known Activations