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

    Neuronpedia

    INDEX
    Explanations

    references to pumps and their operation in various contexts

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

    pump failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iel
    -0.48
     Ira
    -0.47
    hile
    -0.44
     "]
    -0.43
    Id
    -0.42
    ☆☆☆☆
    -0.42
    ever
    -0.42
    BeforeAll
    -0.41
    sole
    -0.41
     Willis
    -0.41
    POSITIVE LOGITS
     pump
    1.24
    Pump
    1.20
     PUMP
    1.19
     Pump
    1.16
    pump
    1.13
     pumps
    1.13
     Pumps
    1.08
     pumped
    0.95
     pumping
    0.94
    pompa
    0.94
    Act Density 0.005%

    No Known Activations