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

    Neuronpedia

    INDEX
    Explanations

    some critics or analysts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ный
    0.67
     or
    0.65
    ively
    0.61
    ного
    0.60
    Боль
    0.60
    Эти
    0.60
    騨
    0.60
    शुदा
    0.60
     или
    0.59
     them
    0.59
    POSITIVE LOGITS
    besides
    1.10
     besides
    1.06
     türlü
    0.91
     trong
    0.88
     within
    0.87
     beside
    0.83
     succinctly
    0.82
     encompassing
    0.82
     dalam
    0.81
     dozen
    0.80
    Act Density 0.141%

    No Known Activations