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

    Neuronpedia

    INDEX
    Explanations

    GNU compilers and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    1.52
    ي
    1.48
    سال
    1.45
    trees
    1.43
    𝐨
    1.39
    THING
    1.36
    tempo
    1.28
     Veja
    1.27
     Wirklich
    1.27
    കൊണ്ട്
    1.27
    POSITIVE LOGITS
    ру
    1.65
    izability
    1.48
    ността
    1.41
    izable
    1.40
    А
    1.39
    もある
    1.35
    க்கு
    1.34
    하여
    1.34
    등학교
    1.34
    ությ
    1.33
    Act Density 0.040%

    No Known Activations