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

    Neuronpedia

    INDEX
    Explanations

    system identifiers and addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treino
    -0.09
    yrics
    -0.08
    充值
    -0.08
    歌词
    -0.08
     stirred
    -0.08
     fueling
    -0.08
     bevatten
    -0.08
    _dates
    -0.08
    _training
    -0.07
     Shipment
    -0.07
    POSITIVE LOGITS
    .host
    0.09
    (host
    0.08
    Pkg
    0.08
    assign
    0.08
    Host
    0.08
    .hostname
    0.08
     commentator
    0.08
     assignments
    0.08
    Client
    0.08
    CLIENT
    0.08
    Act Density 0.003%

    No Known Activations