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

    Neuronpedia

    INDEX
    Explanations

    any other information or scenario

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stricken
    0.54
     speeding
    0.52
     overcrowding
    0.51
     ui
    0.49
     NRG
    0.49
     UI
    0.48
    msup
    0.48
    JlcG
    0.48
     NAND
    0.47
     permeates
    0.47
    POSITIVE LOGITS
    ები
    0.52
     außerdem
    0.49
    ాలని
    0.45
    లి
    0.43
    ró
    0.43
     Inoltre
    0.42
     además
    0.42
     Nói
    0.41
    ální
    0.41
    Й
    0.40
    Act Density 0.002%

    No Known Activations