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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structures

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

    code tokens and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.63
     Anſ
    -0.59
     faſt
    -0.57
    tagHelperRunner
    -0.56
    kháu
    -0.54
     ſtand
    -0.52
     unſ
    -0.50
     greateſt
    -0.49
    balleur
    -0.49
     Inſ
    -0.48
    POSITIVE LOGITS
     ProtoMessage
    0.54
     Carmelo
    0.41
     Rose
    0.40
    UpInside
    0.40
     Marks
    0.38
     QtWidgets
    0.38
     Simon
    0.38
     Blair
    0.37
    stoel
    0.37
     Kirk
    0.36
    Act Density 0.971%

    No Known Activations