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

    Neuronpedia

    INDEX
    Explanations

    structured data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parity
    -0.07
    wie
    -0.07
     opportunity
    -0.07
     利
    -0.06
    operations
    -0.06
     inform
    -0.06
     contractual
    -0.06
     immersive
    -0.06
    -0.06
     receipt
    -0.06
    POSITIVE LOGITS
     authDomain
    0.07
     Olympia
    0.06
    flamm
    0.06
     excelente
    0.06
    _pes
    0.06
    _BOOK
    0.06
    ━━━━━━━━━━━━━━━━
    0.06
     شاه
    0.06
    |[
    0.06
    ――
    0.06
    Act Density 0.002%

    No Known Activations