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

    Neuronpedia

    INDEX
    Explanations

    how long it takes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patterns
    0.59
     helping
    0.58
     sélectionnés
    0.58
    lemme
    0.58
     experimented
    0.57
    </h1>
    0.57
     gap
    0.57
    ienie
    0.57
     imputation
    0.56
     regulations
    0.55
    POSITIVE LOGITS
    NonQuery
    0.66
    ரும்பு
    0.64
    Flatten
    0.63
    _:
    0.62
    glEnd
    0.62
    でしょう
    0.62
    duplicate
    0.61
    getic
    0.61
    jpeg
    0.60
    だろう
    0.60
    Act Density 0.002%

    No Known Activations