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

    Neuronpedia

    INDEX
    Explanations

    programming structures and language syntax

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

    callback `cb` parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.35
    CTC
    -0.34
        
    -0.34
     tips
    -0.33
     random
    -0.33
     over
    -0.32
    Liên
    -0.32
    く
    -0.32
    Q
    -0.32
     af
    -0.32
    POSITIVE LOGITS
    expandindo
    0.74
    GEBURTSDATUM
    0.69
     kasarigan
    0.69
    0.68
    parsedMessage
    0.68
     дописавши
    0.66
    GEBURTS
    0.66
     noDo
    0.65
    RotationOrder
    0.65
     createState
    0.65
    Act Density 0.016%

    No Known Activations