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

    Neuronpedia

    INDEX
    Explanations

    AI "developer mode" evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     batalha
    -0.08
     привлекатель
    -0.08
    ilha
    -0.08
     автор
    -0.08
     falla
    -0.08
    fall
    -0.08
     апп
    -0.08
     MINI
    -0.08
    弗
    -0.08
     triumph
    -0.08
    POSITIVE LOGITS
     purposes
    0.10
    用途
    0.09
    Experiment
    0.09
    .Test
    0.08
    目的
    0.08
    567
    0.08
     exploring
    0.08
     Case
    0.08
     Experiment
    0.08
     testing
    0.08
    Act Density 0.051%

    No Known Activations