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

    Neuronpedia

    INDEX
    Explanations

    Access to water

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solidity
    -0.08
     pessim
    -0.08
     profitability
    -0.07
     callbacks
    -0.07
     Call
    -0.07
     blackjack
    -0.07
     effectiveness
    -0.07
     profits
    -0.07
     modifiers
    -0.07
    Rol
    -0.07
    POSITIVE LOGITS
     potable
    0.14
     পানি
    0.13
     água
    0.12
     الماء
    0.12
     પાણી
    0.11
     watering
    0.11
     uống
    0.11
     abaste
    0.11
     водой
    0.11
     воды
    0.11
    Act Density 0.034%

    No Known Activations