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

    Neuronpedia

    INDEX
    Explanations

    structured text delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    が多く
    1.82
    지
    1.75
    ไม่
    1.74
    age
    1.73
    নি
    1.70
    자
    1.66
    ства
    1.63
    AD
    1.63
    ship
    1.61
    து
    1.56
    POSITIVE LOGITS
     batas
    1.83
     extérieure
    1.80
     puissiez
    1.77
     الخارج
    1.74
    ن
    1.73
    ಿಯನ್
    1.63
     Repert
    1.62
     Aéroport
    1.61
     Respondents
    1.60
     vaiht
    1.60
    Act Density 0.046%

    No Known Activations