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

    Neuronpedia

    INDEX
    Explanations

    references to crosses and cruciform structures in various contexts

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

    cross or crosses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     @"/
    -0.49
    Cartney
    -0.47
    MemoryWarning
    -0.46
    IUrlHelper
    -0.44
    GraphicsUnit
    -0.43
    tenham
    -0.42
    الدراسه
    -0.41
    igot
    -0.41
     PRL
    -0.40
    dersfield
    -0.40
    POSITIVE LOGITS
     cross
    1.88
    cross
    1.78
     Cross
    1.71
    Cross
    1.66
     CROSS
    1.66
    CROSS
    1.55
     crosses
    1.51
     crossing
    1.38
     crossed
    1.27
    crossing
    1.22
    Act Density 0.015%

    No Known Activations