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

    Neuronpedia

    INDEX
    Explanations

    technology compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     다시
    0.97
     CSA
    0.92
     AHA
    0.92
     디
    0.91
     PDA
    0.91
     그리고
    0.89
    শত
    0.87
    ওনা
    0.87
     PAF
    0.87
     CERN
    0.86
    POSITIVE LOGITS
     differs
    1.03
     creates
    0.96
     caters
    0.94
     brings
    0.87
     combines
    0.87
     expands
    0.86
     provides
    0.85
     outperforms
    0.84
     delivers
    0.83
    represents
    0.82
    Act Density 0.289%

    No Known Activations