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

    Neuronpedia

    INDEX
    Explanations

    programming and coding syntax structures

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

    Each, NPR, Compared, Regarding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.61
     '\\;'
    -0.59
    EndGlobalSection
    -0.58
    Personensuche
    -0.57
    featureID
    -0.56
    Източници
    -0.56
     MainAxisSize
    -0.56
    SequentialGroup
    -0.56
    ]")]
    -0.55
     noDo
    -0.54
    POSITIVE LOGITS
    Fq
    0.36
     насељу
    0.35
     predictive
    0.34
     Exact
    0.33
    落
    0.32
     issues
    0.32
     Eins
    0.32
     predicted
    0.32
    :✨
    0.31
    iss
    0.31
    Act Density 0.049%

    No Known Activations