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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    澈
    0.77
     උප
    0.76
    ume
    0.68
    াজে
    0.67
    лох
    0.67
    ᅧ
    0.66
    েন্টে
    0.66
    ülő
    0.63
    aleza
    0.63
    arrants
    0.63
    POSITIVE LOGITS
     ఆఫ్
    0.82
    Ⲥ
    0.80
     jod
    0.78
     programma
    0.77
     unanim
    0.77
     haha
    0.76
     Đây
    0.75
    ﮩ
    0.74
     sadde
    0.73
    起床
    0.73
    Act Density 0.019%

    No Known Activations