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

    Neuronpedia

    INDEX
    Explanations

    bullet points with explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uzione
    0.48
    sorting
    0.48
    servicetime
    0.47
    rend
    0.47
    ہرے
    0.46
    醐
    0.45
    紂
    0.44
     involving
    0.44
    ният
    0.43
    urde
    0.43
    POSITIVE LOGITS
     classrooms
    0.47
    LEX
    0.45
     contener
    0.45
    BE
    0.43
     Asia
    0.43
     minds
    0.43
     asia
    0.43
    豆瓣
    0.43
    教室
    0.42
     december
    0.42
    Act Density 0.001%

    No Known Activations