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

    Neuronpedia

    INDEX
    Explanations

    mathematical units and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    웨어
    0.81
     casamento
    0.80
     وهي
    0.79
     conviene
    0.79
    প্রিয়
    0.79
     cikin
    0.78
    ੫
    0.78
     욕
    0.78
     botão
    0.77
    راءة
    0.77
    POSITIVE LOGITS
    ла
    0.83
     escort
    0.66
    ㈤
    0.64
    ened
    0.64
     Downing
    0.64
    SIS
    0.64
    ps
    0.63
     Overall
    0.63
    一声
    0.63
    рила
    0.63
    Act Density 0.002%

    No Known Activations