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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utf
    -0.06
     अव
    -0.06
     Conc
    -0.06
    chg
    -0.06
     rampage
    -0.06
    _le
    -0.06
     ((((
    -0.05
    /ph
    -0.05
    .cast
    -0.05
    owan
    -0.05
    POSITIVE LOGITS
     Сп
    0.08
     ],
    0.08
    <void
    0.07
    ٌ
    0.07
    .batch
    0.07
    ibr
    0.07
     Instruments
    0.07
     …↵↵
    0.06
     setUsername
    0.06
     brew
    0.06
    Act Density 0.000%

    No Known Activations