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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    代åĬŀ
    -0.34
     scre
    -0.27
     bothered
    -0.27
     sticker
    -0.26
    æĺķ
    -0.26
    atty
    -0.26
    hel
    -0.25
    å·¾
    -0.25
     oppose
    -0.25
    angu
    -0.24
    POSITIVE LOGITS
    experiment
    0.29
    Experiment
    0.29
     Experiment
    0.28
     experiment
    0.26
     Narr
    0.26
    åĨįåİ»
    0.26
    æ¼Ķç»İ
    0.25
    èµĽåŃ£
    0.25
    å®ŀéªĮ
    0.24
    Narr
    0.24
    Act Density 0.014%

    No Known Activations