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

    Neuronpedia

    INDEX
    Explanations

    term or title definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     思っ
    0.56
     неболь
    0.54
    Với
    0.51
     nhỏ
    0.50
    屋外
    0.50
     使っ
    0.50
    <unused2164>
    0.49
     منت
    0.49
     சிறிய
    0.49
    <unused2117>
    0.49
    POSITIVE LOGITS
     serendip
    0.70
    所謂
    0.70
     terroir
    0.69
     "
    0.64
     '
    0.63
     sogenannte
    0.61
     homeostasis
    0.60
     tzv
    0.60
     minimalism
    0.60
    所谓
    0.59
    Act Density 1.823%

    No Known Activations