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

    Neuronpedia

    INDEX
    Explanations

    mustard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dangling
    -0.08
    reet
    -0.07
     Hobby
    -0.06
    仰
    -0.06
     CancellationToken
    -0.06
    aneous
    -0.06
     reliability
    -0.06
    _deploy
    -0.06
    ertil
    -0.06
     Crown
    -0.06
    POSITIVE LOGITS
     mustard
    0.14
    _mD
    0.07
     passwd
    0.07
    CLUDING
    0.07
    된다
    0.06
    스는
    0.06
    userName
    0.06
    جار
    0.06
     ніж
    0.06
    stringLiteral
    0.06
    Act Density 0.001%

    No Known Activations