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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate negation or the absence of change

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

    not change or stop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Internasional
    -0.49
     vė
    -0.49
     faſt
    -0.48
    queryInterface
    -0.48
    kháu
    -0.48
    ſelves
    -0.47
    窟
    -0.47
    UnknownFieldSet
    -0.46
    artige
    -0.45
     Theſe
    -0.45
    POSITIVE LOGITS
    complexContent
    0.42
     NSCoder
    0.40
    Nevertheless
    0.39
     nonetheless
    0.39
    __.__
    0.37
     entanto
    0.37
    inheritDoc
    0.36
     Apo
    0.36
    ).__
    0.36
     fact
    0.35
    Act Density 0.056%

    No Known Activations