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

    Neuronpedia

    INDEX
    Explanations

    elements related to lists and data structures in programming

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

    Programming code and database operations

    np_acts-logits-general · gemini-2.0-flash

    list of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .}\
    -0.64
    googleapis
    -0.64
    bufio
    -0.62
    GHIJKLM
    -0.62
    ѝ
    -0.61
     Mail
    -0.59
     _)
    -0.59
    ")==
    -0.58
    ureka
    -0.57
    ]='\
    -0.57
    POSITIVE LOGITS
    Personendaten
    0.62
     judiciales
    0.61
     bezeichneter
    0.58
     disponibilités
    0.58
     amables
    0.56
    +#+#
    0.54
     neutre
    0.54
    numerusform
    0.53
    包括
    0.52
    Scénario
    0.52
    Act Density 0.141%

    No Known Activations