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

    Neuronpedia

    INDEX
    Explanations

    often,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    -2.63
    兹
    -1.77
     zout
    -1.70
     lijn
    -1.65
     is
    -1.64
    摑
    -1.59
    秕
    -1.57
    oneer
    -1.56
    quate
    -1.54
    erea
    -1.52
    POSITIVE LOGITS
    蕷
    1.96
     людей
    1.76
     pengurus
    1.75
     benötigt
    1.52
     zweite
    1.48
    情况下
    1.47
    ໊
    1.43
     pensato
    1.41
     друж
    1.41
     dasarnya
    1.40
    Act Density 0.012%

    No Known Activations