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

    Neuronpedia

    INDEX
    Explanations

    Removal/cancellation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ister
    -0.07
    usions
    -0.07
    Paris
    -0.07
    iktig
    -0.07
    ologically
    -0.07
     concerts
    -0.07
     folded
    -0.07
    chestra
    -0.06
     circuits
    -0.06
     killings
    -0.06
    POSITIVE LOGITS
    ุบาล
    0.07
    transport
    0.06
     важ
    0.06
    489
    0.06
     свого
    0.06
     PŘ
    0.06
    ConfigurationException
    0.06
     ника
    0.06
    λοι
    0.06
    esome
    0.06
    Act Density 0.004%

    No Known Activations