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

    Neuronpedia

    INDEX
    Explanations

    references to boxes or similar container-like structures

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

    "box" or its plurals

    np_acts-logits-general · gemini-2.0-flash

    box and boxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.79
    ########.
    -0.75
    rslt
    -0.69
     Ciri
    -0.69
    StreamReader
    -0.68
     pleaſure
    -0.67
    Uli
    -0.67
    withstanding
    -0.67
    DSA
    -0.66
     DSA
    -0.66
    POSITIVE LOGITS
     boxes
    1.83
     box
    1.81
     BOX
    1.79
     Box
    1.78
     Boxes
    1.63
    BOX
    1.60
    box
    1.59
    boxes
    1.56
    Box
    1.51
    Boxes
    1.42
    Act Density 0.102%

    No Known Activations