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

    Neuronpedia

    INDEX
    Explanations

    read the disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    massive
    0.77
     massive
    0.72
     immense
    0.68
     massively
    0.65
    huge
    0.64
    overall
    0.60
     overall
    0.59
    multiple
    0.57
     ultimate
    0.56
    undant
    0.56
    POSITIVE LOGITS
     foodie
    0.86
     handyman
    0.83
     zodat
    0.81
     divertido
    0.80
     약간
    0.78
     giz
    0.76
     psih
    0.76
     sosyal
    0.75
     괜찮
    0.75
     decently
    0.73
    Act Density 0.605%

    No Known Activations