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

    Neuronpedia

    INDEX
    Explanations

    lists of numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ต้องการ
    0.65
     Yum
    0.62
     увеличить
    0.61
     larger
    0.60
     попыта
    0.59
     ৯০
    0.58
     CEC
    0.58
     "$"
    0.58
     Covenant
    0.58
    қу
    0.57
    POSITIVE LOGITS
     Fool
    0.80
     kilku
    0.78
    Nil
    0.75
     Few
    0.73
    Few
    0.71
    apper
    0.70
    fool
    0.69
     кілько
    0.69
    spinlock
    0.69
    ừa
    0.68
    Act Density 0.233%

    No Known Activations