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

    Neuronpedia

    INDEX
    Explanations

    learning style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.89
    claimed
    0.66
    two
    0.61
    Go
    0.59
    ла
    0.59
    between
    0.59
    5
    0.59
    an
    0.59
     mellan
    0.57
    from
    0.57
    POSITIVE LOGITS
     investir
    0.62
    டன்
    0.60
     दट
    0.58
     DREAM
    0.58
     Juli
    0.57
    𝙏
    0.57
     Explor
    0.56
     xt
    0.56
     শক্তির
    0.55
     것이
    0.55
    Act Density 0.022%

    No Known Activations