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

    Neuronpedia

    INDEX
    Explanations

    technology, economics, and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inset
    0.40
    othed
    0.40
     UNSIGNED
    0.39
    ANGE
    0.38
    ™.
    0.37
    tare
    0.37
    ुरा
    0.36
     wooded
    0.36
     objets
    0.36
    unities
    0.36
    POSITIVE LOGITS
     Wikipedia
    0.49
     psychology
    0.47
     Psychology
    0.43
    Myth
    0.42
     Definition
    0.42
     GDP
    0.40
    习近平
    0.40
     ताजमहल
    0.40
     epistemology
    0.39
     definición
    0.39
    Act Density 0.005%

    No Known Activations