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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rest
    -0.07
    Unload
    -0.07
     fire
    -0.07
     heed
    -0.06
     응
    -0.06
     aute
    -0.06
    $client
    -0.06
    _hid
    -0.06
    ตรง
    -0.06
     humid
    -0.06
    POSITIVE LOGITS
     comparing
    0.21
     comparison
    0.21
     comparisons
    0.19
     compared
    0.18
     Comparison
    0.17
     compares
    0.15
    Comparison
    0.14
    comparison
    0.13
     Compared
    0.13
     Compar
    0.12
    Act Density 0.033%

    No Known Activations