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

    Neuronpedia

    INDEX
    Explanations

    illustrate or understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    outer
    0.56
    φος
    0.53
    ങ്ങളിലും
    0.52
    ellen
    0.51
    ment
    0.50
    inner
    0.49
    umes
    0.49
    はもちろん
    0.49
    :
    0.49
     supra
    0.49
    POSITIVE LOGITS
     Đà
    0.72
     piracy
    0.69
     recreational
    0.69
     জনপ্রিয়
    0.68
     leisure
    0.66
     poetry
    0.64
    论文
    0.64
     કેટલાક
    0.63
    幸运
    0.62
     néhány
    0.62
    Act Density 0.003%

    No Known Activations