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

    Neuronpedia

    INDEX
    Explanations

    document excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STD
    -0.08
    CLI
    -0.07
    fwrite
    -0.07
    цю
    -0.06
    mtime
    -0.06
    writes
    -0.06
     Formatter
    -0.06
    nz
    -0.06
    _put
    -0.06
     statutes
    -0.06
    POSITIVE LOGITS
     );↵↵↵
    0.07
     artist
    0.07
    AuthProvider
    0.06
    ».
    0.06
    ard
    0.06
     výj
    0.06
    _lcd
    0.06
     familiar
    0.06
     ünlü
    0.06
     elaborate
    0.06
    Act Density 0.011%

    No Known Activations