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

    Neuronpedia

    INDEX
    Explanations

    sports statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kirche
    -1.00
    дни
    -0.98
    These
    -0.93
    allclose
    -0.82
     industry
    -0.80
    wyk
    -0.80
    GetAll
    -0.78
    ウィン
    -0.77
     sabem
    -0.77
    ଘ
    -0.76
    POSITIVE LOGITS
     will
    1.08
    往往
    0.88
     frumo
    0.83
    釦
    0.82
    ﻦ
    0.82
    owymi
    0.81
     będą
    0.81
    unesse
    0.80
    บอล
    0.80
     penurunan
    0.79
    Act Density 0.005%

    No Known Activations