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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a definition or explanation

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

    defining or explaining phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.45
     lenker
    -0.44
     nawr
    -0.41
    currentColor
    -0.39
    FormTagHelper
    -0.39
     TestBed
    -0.39
    CppMethod
    -0.36
    ۜ
    -0.35
    RectangleBorder
    -0.35
     للمعارف
    -0.34
    POSITIVE LOGITS
     meaning
    0.66
    すな
    0.58
     znaczy
    0.57
     zoude
    0.55
    つまり
    0.55
     Meaning
    0.54
    Meaning
    0.53
     nodeId
    0.52
    meaning
    0.52
    즉
    0.52
    Act Density 0.121%

    No Known Activations