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

    Neuronpedia

    INDEX
    Explanations

    and is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eivät
    0.81
     বললেন
    0.66
     and
    0.64
     wanting
    0.63
     &
    0.63
    They
    0.63
     ஆகியோர்
    0.62
     /
    0.61
    0.61
    都能
    0.59
    POSITIVE LOGITS
     has
    1.93
     is
    1.92
     является
    1.77
     was
    1.59
     represents
    1.59
     differs
    1.58
     possesses
    1.57
     appears
    1.53
     exemplifies
    1.53
     constitutes
    1.52
    Act Density 0.285%

    No Known Activations