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
     受
    -0.07
     dolls
    -0.06
    -contrib
    -0.06
     Chanel
    -0.06
    [random
    -0.06
    alı
    -0.06
    box
    -0.06
    Credential
    -0.06
     Monk
    -0.06
    \Mail
    -0.06
    POSITIVE LOGITS
    eltas
    0.06
    .getCell
    0.06
     ],
    0.06
    Quite
    0.06
    zers
    0.06
     annotate
    0.06
     legitimate
    0.06
     Desmond
    0.06
     Muss
    0.06
    DataSource
    0.06
    Act Density 0.217%

    No Known Activations