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
     Bro
    -0.07
    恨
    -0.07
     здоров
    -0.07
     РФ
    -0.06
     San
    -0.06
     přísluš
    -0.06
     đất
    -0.06
    .population
    -0.06
    Slf
    -0.06
    .fetch
    -0.06
    POSITIVE LOGITS
    μένες
    0.07
     Academic
    0.06
     retired
    0.06
    ustil
    0.06
     explores
    0.06
    ushort
    0.06
    ächst
    0.06
    г
    0.06
    (value
    0.06
    _command
    0.06
    Act Density 0.008%

    No Known Activations