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

    Neuronpedia

    INDEX
    Explanations

    SQL `id` column

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neck
    0.92
    Delay
    0.89
    ﻰ
    0.88
     Dess
    0.87
    ших
    0.87
     intelligent
    0.86
    ച്ച
    0.86
     favor
    0.84
    Electronic
    0.83
    UTC
    0.83
    POSITIVE LOGITS
    empot
    1.60
    leness
    1.39
    aho
    1.27
    daa
    1.26
    yll
    1.18
    rául
    1.18
    AppBsky
    1.17
    köz
    1.13
    ="@+
    1.12
    ntity
    1.12
    Act Density 0.094%

    No Known Activations