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

    Neuronpedia

    INDEX
    Explanations

    Python class definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offend
    -0.06
     野
    -0.06
    .RegularExpressions
    -0.06
     quir
    -0.06
    मर
    -0.06
     HtmlWebpackPlugin
    -0.06
     antlr
    -0.06
    	effect
    -0.06
     testimon
    -0.06
    Так
    -0.06
    POSITIVE LOGITS
     Syrians
    0.06
    ierarchy
    0.06
     hearts
    0.06
    raid
    0.06
    Forms
    0.06
     markedly
    0.06
    _each
    0.06
    atoms
    0.06
    iard
    0.06
    pressive
    0.06
    Act Density 0.013%

    No Known Activations