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

    Neuronpedia

    INDEX
    Explanations

    comparison operators with other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utim
    0.39
    ਜ
    0.38
     Wad
    0.36
     ।
    0.36
     मुह
    0.35
     जूनियर
    0.35
     taas
    0.34
    最後に
    0.34
    ：
    0.34
    জু
    0.33
    POSITIVE LOGITS
     theirs
    0.54
    相手
    0.51
     مشابه
    0.45
     비슷
    0.44
    对方
    0.44
    Yours
    0.43
     상대
    0.42
     hers
    0.42
     Yours
    0.41
    someone
    0.40
    Act Density 0.013%

    No Known Activations