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

    Neuronpedia

    INDEX
    Explanations

    instances of regular expressions and specific programming syntax

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

    before numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    black conservatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </strong>
    -1.08
    </h1>
    -0.77
    </b>
    -0.73
     ddelweddau
    -0.72
    <strong>
    -0.67
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.63
    <em>
    -0.61
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.60
    </u>
    -0.58
    "}>
    -0.58
    POSITIVE LOGITS
    sizeCache
    1.06
     purpoſe
    0.94
    QMetaType
    0.94
     Efq
    0.93
     учё
    0.93
    OGND
    0.92
     visualisation
    0.90
     Diſ
    0.89
    Fordítás
    0.89
     fertiliser
    0.88
    Act Density 1.428%

    No Known Activations