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

    Neuronpedia

    INDEX
    Explanations

    drawing rect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ശ്വാ
    0.35
    レザー
    0.35
    ชีพ
    0.35
    ুরী
    0.33
    नामी
    0.33
     পরিমাণ
    0.32
    ভৃতি
    0.32
    Marion
    0.32
     woodworking
    0.32
    াতাড়ি
    0.32
    POSITIVE LOGITS
     rectángulo
    0.38
    厈
    0.37
    }}-
    0.36
    לא
    0.36
     fale
    0.35
     rectangular
    0.35
     enfrent
    0.35
    는다
    0.35
    日上午
    0.35
     convuls
    0.34
    Act Density 0.001%

    No Known Activations