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

    Neuronpedia

    INDEX
    Explanations

    references to numeric values and their associations in research contexts

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

    Medication identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.74
    mpagne
    -0.74
     geſch
    -0.73
    <unused16>
    -0.71
    <unused68>
    -0.71
    <unused17>
    -0.71
    <unused23>
    -0.71
    <unused14>
    -0.71
    [@BOS@]
    -0.71
    <unused8>
    -0.71
    POSITIVE LOGITS
     Commission
    0.28
     Đây
    0.28
    QMetaType
    0.27
    wachung
    0.27
     này
    0.26
    OptionsMenu
    0.25
     Enfin
    0.25
    <eos>
    0.24
    แดง
    0.24
    中
    0.24
    Act Density 0.156%

    No Known Activations