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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bentley
    -0.07
    นะ
    -0.07
     Academy
    -0.07
     Erik
    -0.07
     Lazar
    -0.06
     specialization
    -0.06
     Narrative
    -0.06
     Costs
    -0.06
    ack
    -0.06
    iber
    -0.06
    POSITIVE LOGITS
     داخل
    0.06
    مند
    0.06
     Да
    0.06
    ją
    0.06
    iving
    0.06
    
    0.06
    ρι
    0.06
     diren
    0.06
    /Desktop
    0.06
    udp
    0.05
    Act Density 0.002%

    No Known Activations