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

    Neuronpedia

    INDEX
    Explanations

    authority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _POLICY
    -0.06
     όμως
    -0.06
    Quotes
    -0.06
    _enabled
    -0.06
     Assistant
    -0.06
     ś
    -0.06
    onomic
    -0.06
     diversos
    -0.06
     IPT
    -0.06
    _qos
    -0.06
    POSITIVE LOGITS
    abella
    0.06
    伙
    0.06
     voucher
    0.06
     realized
    0.06
    asley
    0.06
    TRANSFER
    0.06
     eventType
    0.06
    minimal
    0.06
    ownload
    0.06
    _scaling
    0.06
    Act Density 0.000%

    No Known Activations