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

    Neuronpedia

    INDEX
    Explanations

    the Victorian Age

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hoea
    1.83
     organisers
    1.72
    是个
    1.67
    年は
    1.59
    icillin
    1.59
     Encyclopædia
    1.53
    あるいは
    1.52
     (=
    1.51
    などが
    1.51
     $=$
    1.51
    POSITIVE LOGITS
     centered
    1.82
    7
    1.62
     basic
    1.60
     twofold
    1.59
     rudimentary
    1.55
     limited
    1.50
     fundamentally
    1.49
     simply
    1.49
    6
    1.48
     rooted
    1.47
    Act Density 0.649%

    No Known Activations