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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ことが
    0.73
    HOUSE
    0.72
    屐
    0.69
     குறைவாக
    0.69
    যজ্ঞ
    0.68
    থ
    0.68
    藐
    0.67
     cracking
    0.66
    라우
    0.65
    その
    0.64
    POSITIVE LOGITS
     immigrant
    0.91
    cor
    0.91
    xFF
    0.89
    steel
    0.83
    ATC
    0.81
    傛
    0.81
     خون
    0.79
    ⠀
    0.79
    metals
    0.78
    mus
    0.77
    Act Density 0.099%

    No Known Activations