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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs followed by "can," "could," "have," or "for."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.69
     nothing
    -0.60
    Nothing
    -0.57
     Nothing
    -0.56
     everything
    -0.55
     what
    -0.54
    nothing
    -0.53
     acontece
    -0.51
    DebuggerNonUser
    -0.50
     whatever
    -0.48
    POSITIVE LOGITS
    ItemBackground
    0.62
     >=",
    0.58
     Wikimedijinoj
    0.58
    Personensuche
    0.57
     الرياضيه
    0.55
     autorytatywna
    0.55
    InitVars
    0.55
    DJANGO
    0.55
     Paglinawan
    0.54
    oneofs
    0.52
    Act Density 1.439%

    No Known Activations