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

    Neuronpedia

    INDEX
    Explanations

    information related to law enforcement and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Currency or ability related to incentives

    np_acts-logits-general · gemini-2.0-flash

    can use reward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ControllerTest
    -0.50
    Uninitialized
    -0.48
    SharedCtor
    -0.47
     test
    -0.47
    EDEFAULT
    -0.46
     OFDb
    -0.42
     Origin
    -0.42
    Origin
    -0.42
     Test
    -0.42
    ORIGIN
    -0.41
    POSITIVE LOGITS
    toppers
    0.99
     reward
    0.93
     rewards
    0.88
     Reward
    0.87
    Reward
    0.85
     Rewards
    0.83
    Rewards
    0.82
     recompensa
    0.78
     récompense
    0.75
     Stoppers
    0.75
    Act Density 0.125%

    No Known Activations