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

    Neuronpedia

    INDEX
    Explanations

    Security and borders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unj
    -0.08
    _mov
    -0.08
     Elemental
    -0.08
    .WebDriver
    -0.07
    結合
    -0.07
    傩
    -0.07
     Doch
    -0.06
    ところで
    -0.06
    eut
    -0.06
    Attend
    -0.06
    POSITIVE LOGITS
     resultCode
    0.08
     childs
    0.07
     Caller
    0.07
    >Show
    0.07
    \Models
    0.07
     xml
    0.07
    /m
    0.06
     findings
    0.06
    TL
    0.06
    ير
    0.06
    Act Density 0.022%

    No Known Activations