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

    Neuronpedia

    INDEX
    Explanations

    topics related to changes in educational or organizational practices and community engagement

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

    shifting focus away or on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.46
    ovia
    -0.45
    unteer
    -0.45
    rvats
    -0.45
     propOrder
    -0.44
    -------------</
    -0.43
     quickest
    -0.43
     agrav
    -0.43
    下载附件
    -0.41
    новништво
    -0.40
    POSITIVE LOGITS
     shift
    1.16
     shifted
    0.97
    shift
    0.91
     Shift
    0.87
     shifting
    0.84
     shifts
    0.81
    Instead
    0.81
    shifted
    0.81
    Shift
    0.80
     instead
    0.77
    Act Density 0.093%

    No Known Activations