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

    Neuronpedia

    INDEX
    Explanations

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.40
    version
    0.38
    ',
    0.38
     đích
    0.38
    EMA
    0.37
    Stake
    0.37
    5
    0.37
    Validity
    0.37
    Slate
    0.36
    ab
    0.36
    POSITIVE LOGITS
     interstices
    0.45
     entire
    0.45
     airway
    0.40
     respective
    0.40
     સમગ્ર
    0.40
     kanilang
    0.40
     bowels
    0.39
     walls
    0.39
     periphery
    0.39
     siano
    0.39
    Act Density 0.175%

    No Known Activations