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

    Neuronpedia

    INDEX
    Explanations

    Google DeepMind research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bakufu
    0.60
    اریخ
    0.54
     dimulai
    0.54
     مذکور
    0.53
     Índice
    0.51
     അനുവദ
    0.51
    کی
    0.50
     uygulama
    0.50
    ᚋ
    0.50
     definisi
    0.49
    POSITIVE LOGITS
    ’
    0.52
    at
    0.50
    p
    0.49
    s
    0.48
    g
    0.47
    x
    0.47
     x
    0.47
    onk
    0.45
    6
    0.45
    on
    0.44
    Act Density 0.001%

    No Known Activations