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

    Neuronpedia

    INDEX
    Explanations

    model answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oban
    1.01
    ारक
    0.98
    ạy
    0.94
     heartwarming
    0.91
     splashed
    0.91
     adorable
    0.90
     lovely
    0.89
    uttam
    0.88
    lovely
    0.88
     natoque
    0.87
    POSITIVE LOGITS
     者
    0.72
    벨
    0.66
    সম্পাদক
    0.64
    علي
    0.63
     दख
    0.63
     clinique
    0.62
     초
    0.62
     Cred
    0.61
     Zeta
    0.61
     Mode
    0.61
    Act Density 0.094%

    No Known Activations