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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transporter
    -0.07
     Myth
    -0.07
     carpets
    -0.06
     encoding
    -0.06
     cop
    -0.06
     grooming
    -0.06
    ugador
    -0.06
     crochet
    -0.06
     �
    -0.06
     clothes
    -0.06
    POSITIVE LOGITS
    TriState
    0.08
    erdings
    0.07
    ίων
    0.06
    .createClass
    0.06
    <![
    0.06
     unsett
    0.06
    ificantly
    0.06
     outstanding
    0.06
    remainder
    0.06
    334
    0.06
    Act Density 0.023%

    No Known Activations