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

    Neuronpedia

    INDEX
    Explanations

    ME V

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ոլ
    0.44
     braucht
    0.43
     mū
    0.42
     Everyone
    0.42
     すご
    0.42
     Rooms
    0.42
     everyone
    0.42
     schwierig
    0.41
    ゔ
    0.41
     überprü
    0.40
    POSITIVE LOGITS
     நன்றி
    0.41
    Nim
    0.37
    Lecture
    0.37
    brero
    0.37
    ها
    0.36
    Ex
    0.36
    tesy
    0.34
    pools
    0.34
    ައި
    0.34
    ቀ
    0.33
    Act Density 0.000%

    No Known Activations