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

    Neuronpedia

    INDEX
    Explanations

    Standard gravity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xcuserdata
    0.40
    ர்களே
    0.39
    rafpunkte
    0.38
    Lantern
    0.38
    ські
    0.38
     gratuito
    0.38
    LOCAL
    0.38
    лкой
    0.38
    द्वानी
    0.38
     wides
    0.37
    POSITIVE LOGITS
     Scrub
    0.44
     pursue
    0.39
     prepare
    0.38
     use
    0.38
     Firmware
    0.37
     usare
    0.37
     lyrics
    0.37
     scrub
    0.37
     esprit
    0.37
     Kapp
    0.37
    Act Density 0.000%

    No Known Activations