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

    Neuronpedia

    INDEX
    Explanations

    concepts related to cultural boundaries and their intersections

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

    Exceeding limits, going beyond, or blurring lines

    np_acts-logits-general · gemini-2.0-flash

    transcending boundaries and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.50
     propOrder
    -0.48
    WriteBarrier
    -0.45
    bitField
    -0.45
     дописавши
    -0.42
    aarrggbb
    -0.40
    csak
    -0.40
     հղումներ
    -0.40
    ❹
    -0.40
    flop
    -0.39
    POSITIVE LOGITS
     transcends
    0.61
     يتيمه
    0.54
     transcend
    0.52
     transc
    0.51
     boundaries
    0.47
     الحره
    0.45
     beyond
    0.44
     Boundaries
    0.44
     regardless
    0.44
    struktion
    0.44
    Act Density 0.404%

    No Known Activations