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

    Neuronpedia

    INDEX
    Explanations

    the noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     some
    0.52
     what
    0.51
     another
    0.48
     a
    0.48
     becomes
    0.48
     algumas
    0.47
    跇
    0.46
     underpin
    0.46
     become
    0.45
     those
    0.44
    POSITIVE LOGITS
     president
    0.63
     Federalist
    0.57
     restaurant
    0.56
     Himalayas
    0.55
     plaintiff
    0.55
     wealthiest
    0.55
     protagonist
    0.54
     defendant
    0.53
     Louvre
    0.53
     Dalai
    0.53
    Act Density 0.012%

    No Known Activations