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

    Neuronpedia

    INDEX
    Explanations

    questions and mathematical functions or prompts

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

    solving math problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.59
    DoubleQuotes
    -0.57
    Controllo
    -0.57
    AddTagHelper
    -0.56
    WriteTagHelper
    -0.56
     createState
    -0.54
     defaultstate
    -0.52
    parsedMessage
    -0.52
    ſelves
    -0.52
    -0.51
    POSITIVE LOGITS
    <eos>
    0.42
    It
    0.41
    This
    0.39
    I
    0.39
     I
    0.39
     A
    0.39
     Gher
    0.38
     صرف
    0.38
     It
    0.37
    entuh
    0.37
    Act Density 0.006%

    No Known Activations