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

    Neuronpedia

    INDEX
    Explanations

    specific technical concepts related to modeling and algorithms

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

    binary addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.52
     bounce
    -0.41
    terase
    -0.40
    iedo
    -0.38
     stimulation
    -0.38
     chip
    -0.37
    listFiles
    -0.37
     fail
    -0.37
    ticides
    -0.37
     裕
    -0.37
    POSITIVE LOGITS
     للمعارف
    0.61
     дописавши
    0.54
    hoeddwyd
    0.52
     Monfieur
    0.50
     beginnetje
    0.50
    parsedMessage
    0.48
     utafitiHapana
    0.47
     unknownFields
    0.46
     ainfi
    0.45
    الحياه
    0.45
    Act Density 0.455%

    No Known Activations