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

    Neuronpedia

    INDEX
    Explanations

    press Enter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DBGPRINT
    0.52
     Oggi
    0.52
     tüket
    0.50
     нагре
    0.47
     humidifier
    0.47
     содержит
    0.47
     contienen
    0.46
     кушымта
    0.46
     huge
    0.45
     óptica
    0.45
    POSITIVE LOGITS
    물
    0.46
    在這個
    0.44
    इस
    0.40
    egos
    0.40
    ænd
    0.40
    回目の
    0.39
    oured
    0.39
    candidate
    0.39
     antagonists
    0.39
     culprits
    0.38
    Act Density 0.005%

    No Known Activations