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

    Neuronpedia

    INDEX
    Explanations

    lines of code involving delimiters and newline management

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

    start or end markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.53
     auroit
    -0.50
    AccessorTable
    -0.50
     pouvoit
    -0.50
    WriteTagHelper
    -0.49
    LabelTagHelper
    -0.49
    thâu
    -0.47
    Hentet
    -0.47
     ſind
    -0.47
    Autoritní
    -0.47
    POSITIVE LOGITS
     previous
    0.65
     ending
    0.64
     next
    0.62
     preceding
    0.61
     poprzed
    0.60
     start
    0.58
     ended
    0.58
     Previous
    0.57
     abrupt
    0.56
     nächste
    0.56
    Act Density 0.095%

    No Known Activations