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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their formatting in the text

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

    character encoding in html/xml

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.96
    niſſe
    -0.93
     InputDecoration
    -0.93
    ſſung
    -0.93
    iſchen
    -0.91
     deſſen
    -0.90
     témoig
    -0.88
     vooz
    -0.88
    ðsíða
    -0.87
     ſeines
    -0.87
    POSITIVE LOGITS
    8
    0.64
    StandardCharsets
    0.57
     charset
    0.43
    7
    0.38
     civilización
    0.33
    9
    0.33
    ,
    0.32
    UTF
    0.32
    6
    0.31
     encoding
    0.31
    Act Density 0.001%

    No Known Activations