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

    Neuronpedia

    INDEX
    Explanations

    United States official designations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    -2.45
    相変わらず
    -2.36
    色々と
    -2.33
    凄く
    -2.22
    に行って
    -2.20
    マジで
    -2.14
    ホント
    -2.13
    仕方ない
    -2.13
    気付
    -2.11
    3
    -2.11
    POSITIVE LOGITS
    ”)
    2.23
     of
    2.06
    “
    2.02
    "]);
    1.99
                   
    1.96
     There
    1.93
     oktober
    1.92
    </h3>
    1.92
     (“
    1.91
    ”.
    1.87
    Act Density 0.038%

    No Known Activations