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

    Neuronpedia

    INDEX
    Explanations

    words starting with em

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atted
    0.49
     Something
    0.49
    Ahh
    0.44
    inizin
    0.44
    徃
    0.43
     समझौता
    0.43
     нещо
    0.42
    Something
    0.42
    ্মদ
    0.42
    િંગ
    0.42
    POSITIVE LOGITS
     Em
    0.88
    Em
    0.85
     em
    0.84
     emph
    0.68
     EM
    0.65
     EMB
    0.65
     Empor
    0.60
     emancipation
    0.59
     emot
    0.58
     ém
    0.57
    Act Density 0.041%

    No Known Activations