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

    Neuronpedia

    INDEX
    Explanations

    Databases and file systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PyErr
    -0.08
     hardcoded
    -0.07
    _WRAP
    -0.07
    (outfile
    -0.07
     Cut
    -0.07
    -linear
    -0.07
     cut
    -0.07
     Bingo
    -0.06
    Partition
    -0.06
    .cpp
    -0.06
    POSITIVE LOGITS
     harassment
    0.06
    هداف
    0.06
    漢
    0.06
    431
    0.06
     outfits
    0.06
     devastated
    0.06
    endas
    0.05
    งส
    0.05
    Today
    0.05
    920
    0.05
    Act Density 0.029%

    No Known Activations