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

    Neuronpedia

    INDEX
    Explanations

    strings and their formats in programming and coding contexts

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

    written, converting, expressing, using data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.45
    agle
    -0.37
    SequentialGroup
    -0.35
    fillText
    -0.34
     occupé
    -0.33
    tizia
    -0.33
     Tuch
    -0.32
     جدا
    -0.32
     Angel
    -0.31
     gele
    -0.31
    POSITIVE LOGITS
     written
    0.68
     expressed
    0.66
    expressed
    0.62
     convert
    0.60
     denominated
    0.59
     Convert
    0.59
    CONVERT
    0.59
     using
    0.58
     converted
    0.57
    written
    0.57
    Act Density 0.144%

    No Known Activations