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

    Neuronpedia

    INDEX
    Explanations

    holocaust happened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dSample
    0.46
    প্রশ
    0.45
    襪
    0.42
     стрелецкой
    0.42
    profitLoss
    0.40
    Richmond
    0.40
    曺
    0.40
    منى
    0.39
     لنا
    0.39
    軲
    0.39
    POSITIVE LOGITS
    tip
    0.46
     game
    0.40
    ch
    0.39
    do
    0.39
     hasn
    0.38
     expected
    0.38
     yet
    0.38
     contributor
    0.38
    rot
    0.37
     gazed
    0.37
    Act Density 0.000%

    No Known Activations