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

    Neuronpedia

    INDEX
    Explanations

    json blob

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h3>
    0.57
     Rentals
    0.56
     cultivators
    0.51
    </h2>
    0.50
    點
    0.50
     Dealers
    0.48
     Supervisors
    0.48
     ฟัง
    0.48
     ฝึก
    0.47
     Voz
    0.47
    POSITIVE LOGITS
    ).
    0.51
     percentuale
    0.51
    t
    0.50
    i
    0.48
     вследствие
    0.48
    од
    0.47
    a
    0.47
    j
    0.47
     supposedly
    0.45
     purportedly
    0.45
    Act Density 0.000%

    No Known Activations