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

    Neuronpedia

    INDEX
    Explanations

    suitability detector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     チェック
    0.70
    丁寧に
    0.68
    पूर्वक
    0.63
    кола
    0.63
    prisingly
    0.63
     осталось
    0.62
     પ્રેમ
    0.62
    antemente
    0.61
    ણે
    0.60
     orgullo
    0.60
    POSITIVE LOGITS
     suitable
    4.05
     suited
    3.90
     Suitable
    3.90
    Suitable
    3.84
    适合
    3.81
    suitable
    3.75
    suited
    3.60
     suitability
    3.46
     suits
    3.39
     suit
    3.37
    Act Density 1.481%

    No Known Activations