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

    Neuronpedia

    INDEX
    Explanations

    multilingual or code/technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    媜
    0.51
    agn
    0.48
    ولة
    0.47
    aren
    0.46
     intends
    0.46
    agonist
    0.46
    amt
    0.46
    电机
    0.45
    azi
    0.45
    lovakia
    0.44
    POSITIVE LOGITS
    ↵
    0.54
    निक
    0.54
    h
    0.50
    ע
    0.49
    革命
    0.49
    ма
    0.49
    п
    0.48
     nug
    0.46
    ح
    0.46
    S
    0.45
    Act Density 0.000%

    No Known Activations