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

    Neuronpedia

    INDEX
    Explanations

    जीवन से जुड़े विचार

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ஸ்ட்
    0.52
    ಸ್ಟ್
    0.50
    ﻋ
    0.47
    ﺸ
    0.46
    ্স্ট
    0.46
    ₩
    0.46
    ಸ್ಪ
    0.45
    ᵗ
    0.43
     sh
    0.43
     allotment
    0.43
    POSITIVE LOGITS
     हमरे
    0.47
     सबै
    0.45
     जाए
    0.44
    0.43
     लागे
    0.42
     dwell
    0.40
     kahe
    0.40
     कहे
    0.39
     gacche
    0.39
     Tore
    0.39
    Act Density 0.003%

    No Known Activations