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

    Neuronpedia

    INDEX
    Explanations

    highly specific numerical or mathematical data points and relationships

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

    Text references within square brackets

    np_acts-logits-general · gemini-2.0-flash

    citations and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InStock
    -0.56
    cydow
    -0.48
     Besar
    -0.48
     Gottesdienst
    -0.48
     propres
    -0.48
     Gw
    -0.45
     Own
    -0.44
    سكر
    -0.44
    mius
    -0.44
    ואר
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.85
    TagHelper
    0.76
    EndGlobalSection
    0.68
     utafitiHapana
    0.66
    (!__
    0.64
    principalTable
    0.59
    \{\\
    0.58
    >{@
    0.57
    сылкі
    0.56
    новниш
    0.55
    Act Density 0.925%

    No Known Activations