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

    Neuronpedia

    INDEX
    Explanations

    patterns involving scientific units and measurements

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

    scientific notation numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ControllerAdvice
    -0.28
     roues
    -0.28
     CanadaChoose
    -0.27
     call
    -0.27
     doPost
    -0.27
     folks
    -0.26
     man
    -0.26
    Quellen
    -0.26
     su
    -0.25
    Call
    -0.25
    POSITIVE LOGITS
     AssemblyTitle
    0.72
    iſchen
    0.71
    setVerticalGroup
    0.67
     trillion
    0.66
    <pad>
    0.66
     Италијани
    0.66
    <unused52>
    0.66
    <unused28>
    0.66
    <unused14>
    0.66
    <unused8>
    0.65
    Act Density 0.084%

    No Known Activations