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

    Neuronpedia

    INDEX
    Explanations

    vertebrae and ribs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.53
    e
    0.49
    та
    0.46
    1
    0.46
    thed
    0.43
    THERE
    0.43
     duquel
    0.43
     causada
    0.43
    aaaa
    0.42
    i
    0.42
    POSITIVE LOGITS
     It
    0.66
    ↵↵
    0.55
     it
    0.55
     for
    0.52
    它
    0.52
    مو
    0.44
     to
    0.43
    ions
    0.43
    ून
    0.42
    ably
    0.41
    Act Density 0.000%

    No Known Activations