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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GitHub
    -0.07
    .setter
    -0.07
    isNew
    -0.07
    _fixture
    -0.07
    .Sql
    -0.06
     Lease
    -0.06
    _config
    -0.06
     Huang
    -0.06
    Destroy
    -0.06
    Qual
    -0.06
    POSITIVE LOGITS
     bidding
    0.07
    ोक
    0.06
     charities
    0.06
    versations
    0.06
     кош
    0.06
     trom
    0.06
     रस
    0.06
     agents
    0.06
     CART
    0.06
    ﾍ
    0.06
    Act Density 0.003%

    No Known Activations