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

    Neuronpedia

    INDEX
    Explanations

    QQ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /a
    -0.06
    ring
    -0.06
    <Type
    -0.06
     pf
    -0.06
    .Package
    -0.06
    .Combine
    -0.06
    them
    -0.06
     Picture
    -0.06
    _cm
    -0.06
    Plugin
    -0.06
    POSITIVE LOGITS
     mlad
    0.07
     vì
    0.07
    741
    0.07
    836
    0.06
     Electricity
    0.06
     держави
    0.06
    ||||
    0.06
     EventArgs
    0.06
     Jen
    0.06
     +:+
    0.06
    Act Density 0.004%

    No Known Activations