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

    Neuronpedia

    INDEX
    Explanations

    coding-related functions and methods in programming

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

    C++ programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.79
     المعيارى
    -0.77
     queſta
    -0.73
    ValueStyle
    -0.70
     Wikimedijinoj
    -0.69
     ujednoznacz
    -0.69
     emailAlready
    -0.65
     kasarigan
    -0.63
    farin
    -0.62
    fillType
    -0.61
    POSITIVE LOGITS
     doit
    0.42
     تق
    0.34
     ability
    0.33
     tud
    0.32
     guarantee
    0.32
    multicolumn
    0.32
     departmental
    0.32
     serve
    0.31
     Jennie
    0.30
     رج
    0.30
    Act Density 0.006%

    No Known Activations