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

    Neuronpedia

    INDEX
    Explanations

    url followed by equals and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     折りたたみ
    -0.85
     DBNull
    -0.83
     becoming
    -0.80
     зато
    -0.80
    配慮
    -0.79
    に変更
    -0.77
    好不好
    -0.77
    デメリット
    -0.76
    ==-
    -0.76
    romole
    -0.76
    POSITIVE LOGITS
     "
    2.08
     “
    1.79
     "";
    1.77
     “[
    1.44
     "[
    1.33
     "";
    1.26
     “…
    1.23
     ""
    1.20
    ";
    1.14
     "<
    1.13
    Act Density 0.020%

    No Known Activations