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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and system design

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

    counting to three

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.73
     EconPapers
    -0.65
    RegressionTest
    -0.54
    Autoritní
    -0.51
     للمعارف
    -0.49
    galus
    -0.48
    thâu
    -0.48
     externi
    -0.48
    uxxxx
    -0.47
    enderror
    -0.46
    POSITIVE LOGITS
     üç
    0.59
    三人
    0.57
     three
    0.56
    Three
    0.53
     trois
    0.52
    三
    0.51
    three
    0.50
    三個
    0.50
     três
    0.49
     három
    0.49
    Act Density 0.232%

    No Known Activations