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

    Neuronpedia

    INDEX
    Explanations

    postal service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.52
    い
    1.06
    ς
    1.05
    i
    1.02
     é
    1.00
     hề
    1.00
    ä
    1.00
     doch
    0.99
    স
    0.99
     è
    0.97
    POSITIVE LOGITS
    ته
    1.03
    ную
    0.98
     motivic
    0.98
    nosť
    0.97
    phine
    0.96
     tcpHeader
    0.96
     parietal
    0.93
     apertures
    0.93
     voltmeter
    0.91
    ПУ
    0.89
    Act Density 0.001%

    No Known Activations