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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dent
    -0.07
     Butt
    -0.07
     Mohamed
    -0.07
    anning
    -0.07
     recently
    -0.06
    undos
    -0.06
     Queens
    -0.06
    Walker
    -0.06
    uced
    -0.06
    -Col
    -0.06
    POSITIVE LOGITS
    <Transform
    0.06
    본
    0.06
     colder
    0.06
    .GetKeyDown
    0.06
     crossorigin
    0.06
     بسته
    0.06
    itters
    0.06
     tôi
    0.06
    groupBy
    0.06
    verbs
    0.06
    Act Density 0.004%

    No Known Activations