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

    Neuronpedia

    INDEX
    Explanations

    network performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    1.79
    á
    1.44
    utiérrez
    1.42
    тім
    1.34
    ouring
    1.31
    де
    1.29
    то
    1.28
    ция
    1.26
    нта
    1.26
    pores
    1.26
    POSITIVE LOGITS
     steel
    1.44
    Wireless
    1.35
     non
    1.23
    CH
    1.23
     IEEE
    1.21
     wave
    1.17
     Standards
    1.16
    ek
    1.16
     wireless
    1.16
     fare
    1.15
    Act Density 0.601%

    No Known Activations