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

    Neuronpedia

    INDEX
    Explanations

    questions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ากาศ
    0.45
     Exptl
    0.41
     kennt
    0.40
    㓶
    0.40
     বিনিয়োগ
    0.40
    gdock
    0.40
    䡊
    0.39
     ಕೇಂದ್ರ
    0.39
     informiert
    0.39
    が通販
    0.39
    POSITIVE LOGITS
     explanation
    0.43
     Explanation
    0.40
     Hint
    0.38
     awkward
    0.38
     grizz
    0.37
    Explanation
    0.37
    writ
    0.37
    to
    0.35
    cal
    0.35
    Ну
    0.35
    Act Density 0.000%

    No Known Activations