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

    Neuronpedia

    INDEX
    Explanations

    financial figures, particularly in the context of theft or losses

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

    amounts, billions, millions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HCO
    -0.33
     pop
    -0.32
     edge
    -0.30
     sup
    -0.30
    同
    -0.30
     aper
    -0.30
     pat
    -0.29
     Tama
    -0.29
     EU
    -0.28
    ptonshire
    -0.28
    POSITIVE LOGITS
     ModelExpression
    0.68
     CWE
    0.65
     AssemblyVersion
    0.65
    RegressionTest
    0.59
     Signalez
    0.58
    ioutil
    0.57
     <>",
    0.57
     transfieras
    0.56
    #+#
    0.56
    Rüyada
    0.56
    Act Density 0.043%

    No Known Activations