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

    Neuronpedia

    INDEX
    Explanations

    tend to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🎪
    0.42
     있었
    0.40
    മുണ്ട
    0.38
    emerg
    0.38
     sucedió
    0.36
    📹
    0.36
     sicherlich
    0.36
     কৌশ
    0.36
     ocorreu
    0.36
     இருந்தது
    0.36
    POSITIVE LOGITS
     tend
    0.96
     tends
    0.95
     notoriously
    0.83
     tienden
    0.77
     cenderung
    0.76
     tended
    0.73
     tendency
    0.73
     tende
    0.71
     tiende
    0.70
     склон
    0.67
    Act Density 0.033%

    No Known Activations