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

    Neuronpedia

    INDEX
    Explanations

    struct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.94
     EconPapers
    -0.93
    GEBURTSDATUM
    -0.90
    findpost
    -0.87
     بيها
    -0.85
    aarrggbb
    -0.84
     AssemblyProduct
    -0.82
    ensement
    -0.82
     Signalez
    -0.82
    NUMX
    -0.81
    POSITIVE LOGITS
    not
    0.36
     -
    0.32
    G
    0.31
     –
    0.30
    Not
    0.30
    E
    0.30
    th
    0.30
    est
    0.29
     (
    0.29
    a
    0.28
    Act Density 0.002%

    No Known Activations