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

    Neuronpedia

    INDEX
    Explanations

    c++ programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fell
    0.71
     sign
    0.65
    манов
    0.65
    ilight
    0.64
     corn
    0.64
     PLACE
    0.63
    ctic
    0.62
     place
    0.62
    스러운
    0.61
     DeepCollection
    0.61
    POSITIVE LOGITS
    alkyl
    0.75
    ++
    0.72
    ontiti
    0.70
    ausal
    0.70
     अफ
    0.68
     ++
    0.66
    ++,
    0.65
    OVER
    0.64
    शे
    0.64
    ++]
    0.63
    Act Density 0.103%

    No Known Activations