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

    Neuronpedia

    INDEX
    Explanations

    specific authors and their notable works

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

    Punctuation followed by discourse markers

    np_acts-logits-general · gemini-2.0-flash

    honestly, surprisingly introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.75
     EconPapers
    -0.73
     للمعارف
    -0.73
     متعلقه
    -0.72
     entanto
    -0.66
    IndentedString
    -0.66
     Paglinawan
    -0.65
     مرئيه
    -0.64
     Normdatei
    -0.63
    richTextPanel
    -0.61
    POSITIVE LOGITS
     admittedly
    0.92
    mittedly
    0.86
     Honestly
    0.83
     Surprisingly
    0.82
    Honestly
    0.81
    Surprisingly
    0.80
     honestly
    0.79
     frankly
    0.75
     Obviously
    0.75
    Obviously
    0.74
    Act Density 0.127%

    No Known Activations