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

    Neuronpedia

    INDEX
    Explanations

    introducing contrast or exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ح
    1.87
    у
    1.84
    在这种
    1.79
    े
    1.74
    ড
    1.66
     homen
    1.66
    स
    1.63
    াল
    1.59
     asemenea
    1.57
    های
    1.56
    POSITIVE LOGITS
    termilk
    2.43
    thole
    2.40
     digress
    2.06
     là
    1.95
     alas
    1.86
     néanmoins
    1.76
    𝑄
    1.76
    tered
    1.74
    lins
    1.64
    ன்மைய
    1.61
    Act Density 0.229%

    No Known Activations