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

    Neuronpedia

    INDEX
    Explanations

    Physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heisenberg
    -1.14
    polation
    -0.55
     voulez
    -0.54
     uwagę
    -0.54
    atorio
    -0.51
    ipts
    -0.51
    ánchez
    -0.51
     cycle
    -0.50
    (!__
    -0.50
    wolle
    -0.50
    POSITIVE LOGITS
    ">—
    0.62
    OGND
    0.61
    +:+
    0.60
    izoen
    0.59
    +#+#
    0.59
    contentLoaded
    0.57
    χρι
    0.57
     Upan
    0.57
    GEBURTSDATUM
    0.57
    ItemBackground
    0.56
    Act Density 1.653%

    No Known Activations