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

    Neuronpedia

    INDEX
    Explanations

    but, or, and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    牍
    0.44
    vänd
    0.42
     любых
    0.42
    ход
    0.41
    πό
    0.41
    とは
    0.41
    плы
    0.40
     непосред
    0.40
     गोद
    0.40
    }}}{\
    0.40
    POSITIVE LOGITS
     chipset
    0.51
     Galleria
    0.47
     Amazon
    0.46
     Sherwood
    0.46
     Device
    0.45
     serotonin
    0.45
     boutique
    0.44
    ICKEL
    0.44
     Crimson
    0.43
     Rendering
    0.43
    Act Density 0.002%

    No Known Activations