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

    Neuronpedia

    INDEX
    Explanations

    instructions and confirmations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    หว
    -0.07
     insult
    -0.07
    料理
    -0.06
     mnoha
    -0.06
     sushi
    -0.06
     brings
    -0.06
     Vegan
    -0.06
    iệm
    -0.06
    activo
    -0.06
     หล
    -0.06
    POSITIVE LOGITS
    .policy
    0.07
    _temperature
    0.06
    τι
    0.06
    agedList
    0.06
    _results
    0.06
    ichtet
    0.06
    ैल
    0.06
    _datasets
    0.06
    _engine
    0.06
    .console
    0.06
    Act Density 0.022%

    No Known Activations