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

    Neuronpedia

    INDEX
    Explanations

    Official government websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfer
    0.52
     protesting
    0.52
     pouce
    0.51
     cheating
    0.50
     plugin
    0.49
    AR
    0.49
     quits
    0.48
     district
    0.48
     discharge
    0.47
     tax
    0.47
    POSITIVE LOGITS
    บาง
    0.51
    laki
    0.49
    同学们
    0.45
    读者
    0.45
    ees
    0.44
    ipp
    0.44
    优秀
    0.44
    iliz
    0.44
    zq
    0.44
    yll
    0.43
    Act Density 0.003%

    No Known Activations