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

    Neuronpedia

    INDEX
    Explanations

    designed to launch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     популација
    1.13
     metų
    1.07
    ቁ
    1.06
    ことがある
    1.04
    要知道
    1.01
     밖에
    0.98
     ءِ
    0.96
     funzioni
    0.95
     қу
    0.95
     Согласно
    0.94
    POSITIVE LOGITS
    また
    1.26
    ে
    1.15
     sawmill
    1.07
     airspeed
    1.03
    どんどん
    1.03
     swoop
    1.02
    ෝ
    0.99
    지역
    0.99
    planes
    0.97
     porous
    0.96
    Act Density 0.000%

    No Known Activations