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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     كتاب
    -0.07
    -light
    -0.06
     غربی
    -0.06
    ниця
    -0.06
    íveis
    -0.06
     tras
    -0.06
    986
    -0.06
    يكا
    -0.06
    teste
    -0.06
     sibling
    -0.06
    POSITIVE LOGITS
    Youtube
    0.07
    있
    0.07
     rejuven
    0.07
    ]?
    0.06
    vm
    0.06
     eth
    0.06
     {_
    0.06
    OwnProperty
    0.06
    ём
    0.06
    _TOPIC
    0.06
    Act Density 0.000%

    No Known Activations