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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing appreciation or gratitude

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

    "hello world" examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.65
    awtextra
    -0.64
     Infórmanos
    -0.60
     fieldNum
    -0.57
    ➯
    -0.56
     wireType
    -0.54
     propOrder
    -0.54
    ulongan
    -0.53
    unicip
    -0.52
    SequentialGroup
    -0.50
    POSITIVE LOGITS
     
    0.43
    ”
    0.41
    <
    0.41
     disambiguazione
    0.39
    unmodifiable
    0.39
    …
    0.37
     escritura
    0.37
    不敢
    0.35
    I
    0.35
    Referências
    0.35
    Act Density 0.047%

    No Known Activations