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

    Neuronpedia

    INDEX
    Explanations

    after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LC
    0.47
    WP
    0.45
    比如說
    0.41
    ILE
    0.39
    我們會
    0.39
    比如说
    0.39
     Tycho
    0.39
    เดิน
    0.38
    resume
    0.38
     resumed
    0.38
    POSITIVE LOGITS
     luckily
    0.58
    Luckily
    0.51
     Luckily
    0.47
     වැ
    0.45
     onlookers
    0.45
     olvidado
    0.44
     fortunately
    0.43
     लाज
    0.43
     until
    0.42
     yelled
    0.42
    Act Density 0.028%

    No Known Activations