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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     号
    -0.07
    号
    -0.07
     mua
    -0.07
     himself
    -0.06
     Estate
    -0.06
    QA
    -0.06
     время
    -0.06
    四
    -0.06
    uz
    -0.06
     interface
    -0.06
    POSITIVE LOGITS
    'ex
    0.06
    esium
    0.06
    phalt
    0.06
    ehir
    0.06
     tandem
    0.06
     بالم
    0.06
     Patricia
    0.06
     kıs
    0.06
    /ay
    0.05
     */}↵
    0.05
    Act Density 0.020%

    No Known Activations