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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to data structures or programming

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

    Nonsensical strings and uncommon words

    np_acts-logits-general · gemini-2.0-flash

    diagram notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    -0.89
    c
    -0.82
    r
    -0.74
     GenerationType
    -0.67
    FunctionFlags
    -0.66
    n
    -0.65
    CloseOperation
    -0.60
    f
    -0.58
    b
    -0.58
    OGND
    -0.57
    POSITIVE LOGITS
    hoeddwyd
    0.51
     Мексичка
    0.50
    stwa
    0.49
    Skocz
    0.47
     Chy
    0.46
     Jezus
    0.46
    SaveChangesAsync
    0.45
     origines
    0.45
    Leírás
    0.45
    Suara
    0.44
    Act Density 0.199%

    No Known Activations