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

    Neuronpedia

    INDEX
    Explanations

    centimeters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     work
    0.78
    work
    0.66
     pretty
    0.58
     scrubs
    0.57
    agements
    0.56
    arbeit
    0.56
     inventions
    0.54
     someday
    0.54
     decept
    0.54
     работе
    0.54
    POSITIVE LOGITS
    cm
    0.73
     Ltd
    0.66
     テーマ
    0.66
    హ్
    0.66
    getSaveLocation
    0.63
     рамках
    0.62
    তিরিক্ত
    0.61
     Prints
    0.61
     ಸಾ
    0.61
    <unused110>
    0.60
    Act Density 0.001%

    No Known Activations