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

    Neuronpedia

    INDEX
    Explanations

    tools and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bloodstream
    0.43
     serum
    0.41
     living
    0.41
     freshwater
    0.40
     Seattle
    0.40
     blood
    0.40
     nutrition
    0.40
     bleibt
    0.40
     petrochemical
    0.40
     patrol
    0.39
    POSITIVE LOGITS
    相应的
    0.53
    едера
    0.49
     이를
    0.47
     혹은
    0.46
    пами
    0.46
    ერ
    0.46
    }=-\
    0.45
    untuk
    0.44
     idealistic
    0.43
     screenplay
    0.43
    Act Density 0.008%

    No Known Activations