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

    Neuronpedia

    INDEX
    Explanations

    The followed by phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     another
    0.55
     some
    0.54
     to
    0.52
     a
    0.50
     as
    0.50
     the
    0.50
     your
    0.50
     not
    0.50
     has
    0.49
     includes
    0.49
    POSITIVE LOGITS
     wealthiest
    0.68
     protagonist
    0.68
     Taliban
    0.66
     plight
    0.66
     Burj
    0.65
     Himalayas
    0.64
     Israelites
    0.63
     Seahawks
    0.63
     defendant
    0.61
     notion
    0.61
    Act Density 0.068%

    No Known Activations