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

    Neuronpedia

    INDEX
    Explanations

    negative description

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Don
    0.47
    Generally
    0.46
    Ultimately
    0.45
     хозяйства
    0.45
    最初に
    0.44
    Õ
    0.43
    lul
    0.42
     Generally
    0.41
    ছো
    0.41
     साथियों
    0.41
    POSITIVE LOGITS
     unbearable
    0.95
     contradicting
    0.91
     disgraceful
    0.86
     quite
    0.85
     unacceptable
    0.85
     inhum
    0.83
     shameful
    0.82
     debatable
    0.82
     disgusting
    0.82
     monotonous
    0.79
    Act Density 0.137%

    No Known Activations