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

    Neuronpedia

    INDEX
    Explanations

    setup and prerequisites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grundsätzlich
    0.45
    考えると
    0.43
    考虑
    0.41
     módulos
    0.41
    理念
    0.40
     일반적으로
    0.39
     সাধারণত
    0.38
     Dave
    0.37
     методом
    0.37
     típico
    0.37
    POSITIVE LOGITS
    Setup
    0.70
     setup
    0.66
    Instructions
    0.66
     Instructions
    0.65
     instructions
    0.64
    instructions
    0.62
    setup
    0.60
     Setup
    0.57
    SetUp
    0.56
    STRUCTIONS
    0.55
    Act Density 0.002%

    No Known Activations