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

    Neuronpedia

    INDEX
    Explanations

    Basically,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.56
     cao
    0.51
     on
    0.48
     ở
    0.48
     σε
    0.46
     في
    0.45
    ،
    0.45
     ,
    0.45
     پول
    0.44
     în
    0.43
    POSITIVE LOGITS
     คณิตศาสตร์
    0.56
    講解
    0.52
    覬
    0.52
     задания
    0.50
    जानकारी
    0.50
     deoarece
    0.49
    Motivation
    0.48
    Visualization
    0.47
    𒀀
    0.46
    Science
    0.46
    Act Density 0.003%

    No Known Activations