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

    Neuronpedia

    INDEX
    Explanations

    technical and non-English phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PERTY
    0.47
    ஆனால்
    0.40
    珮
    0.40
    ંપ
    0.39
    ьогодні
    0.39
     Kami
    0.39
     jaane
    0.39
     kami
    0.38
     bulunur
    0.38
     aber
    0.38
    POSITIVE LOGITS
     ወ
    0.38
    startX
    0.38
     digging
    0.37
     outflow
    0.37
     backbone
    0.36
     dug
    0.36
     смог
    0.35
     სას
    0.35
     अवल
    0.35
    xlabel
    0.34
    Act Density 0.001%

    No Known Activations