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

    Neuronpedia

    INDEX
    Explanations

    terms related to clarity and understanding in communication

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

    explanatory statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.77
     nonUne
    -0.66
    <pad>
    -0.62
     パンチラ
    -0.62
    <unused3>
    -0.61
    [@BOS@]
    -0.61
    <unused14>
    -0.61
    <unused16>
    -0.61
    <unused42>
    -0.61
    <unused23>
    -0.60
    POSITIVE LOGITS
     cref
    0.32
     Ly
    0.30
     Mal
    0.30
    Ly
    0.28
     ly
    0.27
     Lue
    0.27
    Etern
    0.27
    Mond
    0.27
    ERATION
    0.27
    printStackTrace
    0.26
    Act Density 0.013%

    No Known Activations