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

    Neuronpedia

    INDEX
    Explanations

    similes and analogies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thisobject
    0.50
    像
    0.50
    РА
    0.47
     وذلك
    0.47
     ذلك
    0.47
     này
    0.44
     probl
    0.44
     ಹಾಗೂ
    0.43
     donc
    0.43
    而被
    0.43
    POSITIVE LOGITS
    take
    0.49
    takes
    0.46
    જો
    0.45
    iline
    0.44
    t
    0.44
    nip
    0.44
    e
    0.44
    over
    0.43
    னோ
    0.43
    further
    0.43
    Act Density 0.033%

    No Known Activations