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

    Neuronpedia

    INDEX
    Explanations

    key terms and metrics related to data processing and performance evaluations

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

    AdHoc configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elemField
    -0.75
     betweenstory
    -0.68
     パンチラ
    -0.63
    <unused41>
    -0.62
    <unused28>
    -0.61
    [@BOS@]
    -0.61
    <unused43>
    -0.61
    <unused47>
    -0.61
    <unused74>
    -0.61
    <unused3>
    -0.61
    POSITIVE LOGITS
    :✨
    0.40
    Datuak
    0.39
    zyms
    0.34
    RenderAtEndOf
    0.33
    "}>
    0.31
     décoration
    0.30
    stdc
    0.30
     impianti
    0.30
     Gemeinsame
    0.30
    "]').
    0.30
    Act Density 0.020%

    No Known Activations