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

    Neuronpedia

    INDEX
    Explanations

    any health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    le
    0.59
    a
    0.53
    9
    0.48
     any
    0.47
    8
    0.46
     using
    0.45
     the
    0.44
    an
    0.44
    z
    0.43
    be
    0.42
    POSITIVE LOGITS
     সম্ভাবনা
    0.50
     වැඩි
    0.42
     گزشتہ
    0.41
    নতুন
    0.40
     ಯೋಜನೆ
    0.40
     novoProduto
    0.39
     ಸಮಸ್ಯೆ
    0.39
    原来
    0.38
    μεριν
    0.38
     già
    0.37
    Act Density 0.007%

    No Known Activations