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

    Neuronpedia

    INDEX
    Explanations

    But

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    commands
    -0.07
    กว
    -0.07
    .getConnection
    -0.07
     JComboBox
    -0.07
    包
    -0.07
     PackageManager
    -0.06
     WebDriver
    -0.06
     inout
    -0.06
    _measurement
    -0.06
    .updateDynamic
    -0.06
    POSITIVE LOGITS
     voc
    0.07
    abl
    0.06
     magically
    0.06
    ATA
    0.06
    ata
    0.06
    ovanou
    0.06
    ají
    0.06
     thổ
    0.06
    OldData
    0.06
    -lived
    0.06
    Act Density 0.000%

    No Known Activations