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

    Neuronpedia

    INDEX
    Explanations

    classifications and relationships within datasets or features

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

    classification and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.39
     للمعارف
    -0.36
    EDEFAULT
    -0.35
     geboten
    -0.34
    ówno
    -0.33
     agré
    -0.33
    퀀
    -0.33
     emailAlready
    -0.32
     compét
    -0.31
    了一個
    -0.31
    POSITIVE LOGITS
     Types
    0.54
     classifications
    0.54
    oplayer
    0.49
    AndroidJUnit
    0.47
     Classification
    0.46
     types
    0.45
     classifying
    0.45
    Types
    0.45
     classification
    0.44
    typen
    0.43
    Act Density 0.261%

    No Known Activations