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

    Neuronpedia

    INDEX
    Explanations

    a sporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    readable
    1.04
    เหล่านี้
    0.99
    reader
    0.96
     READER
    0.94
    rui
    0.91
    mane
    0.91
    rotor
    0.90
     keySchedule
    0.90
     Rider
    0.90
    Reader
    0.89
    POSITIVE LOGITS
     David
    1.16
     Dat
    1.14
    David
    1.08
    Dat
    1.06
     Zap
    1.01
     Ap
    0.96
     Don
    0.96
     Dem
    0.95
     Adams
    0.95
    Don
    0.94
    Act Density 0.429%

    No Known Activations