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

    Neuronpedia

    INDEX
    Explanations

    multiple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دونوں
    0.40
     ಬಿ
    0.39
     പഠ
    0.38
    ทั้ง
    0.36
    زب
    0.36
    urney
    0.36
     слу
    0.36
    モバイル
    0.36
     Prz
    0.35
     ნ
    0.35
    POSITIVE LOGITS
     multiple
    0.90
    Multiple
    0.84
     Multiple
    0.79
    multiple
    0.74
    複数
    0.74
     multi
    0.73
     multiplex
    0.69
    multi
    0.69
     multiplicity
    0.69
    Multi
    0.68
    Act Density 0.379%

    No Known Activations