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

    Neuronpedia

    INDEX
    Explanations

    image input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beings
    0.54
     Reyn
    0.50
     shampoos
    0.49
     êtres
    0.49
     orifices
    0.48
     Dislocations
    0.48
     Hegel
    0.47
     transluc
    0.47
     ribosomes
    0.47
     Skyscrapers
    0.47
    POSITIVE LOGITS
    OZ
    0.54
    聚集
    0.49
    OV
    0.48
    Movie
    0.48
     destac
    0.48
    Crypto
    0.48
    p
    0.47
    Spending
    0.45
    g
    0.45
    APPLICATION
    0.45
    Act Density 0.000%

    No Known Activations