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

    Neuronpedia

    INDEX
    Explanations

    numbers and dollar amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     half
    0.75
    half
    0.69
    lib
    0.67
     general
    0.66
    lie
    0.66
     lie
    0.65
     sæ
    0.65
     text
    0.64
    int
    0.62
     decorating
    0.62
    POSITIVE LOGITS
    Trimethyl
    0.80
    Ꮨ
    0.79
     Routed
    0.74
     Gutierrez
    0.74
    $("
    0.71
     Gutiérrez
    0.69
     Guz
    0.68
    撗
    0.68
     पाचन
    0.67
     $("
    0.67
    Act Density 0.051%

    No Known Activations