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

    Neuronpedia

    INDEX
    Explanations

    Code, configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inn
    -0.08
     bugün
    -0.07
     варт
    -0.06
    ın
    -0.06
     Abd
    -0.06
    Jamie
    -0.06
    باد
    -0.06
     bisa
    -0.06
    .poi
    -0.06
    _fixture
    -0.06
    POSITIVE LOGITS
    nant
    0.07
     approximation
    0.07
     override
    0.06
     mur
    0.06
    .dll
    0.06
     externally
    0.06
    을
    0.06
    Selective
    0.06
     ith
    0.06
     Arthur
    0.06
    Act Density 0.001%

    No Known Activations