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

    Neuronpedia

    INDEX
    Explanations

    included, inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hereafter
    0.39
    これから
    0.39
    ឹ
    0.37
    खो
    0.35
    सित
    0.34
     अपॉन
    0.34
     }^{*
    0.34
     занимается
    0.34
    zoa
    0.33
     basit
    0.33
    POSITIVE LOGITS
     included
    2.55
     inclusion
    2.47
    included
    2.30
     Included
    2.28
     вклю
    2.20
    Included
    2.19
    inclusion
    2.13
     Inclusion
    2.11
     inclusión
    2.09
     शामिल
    1.94
    Act Density 0.032%

    No Known Activations