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

    Neuronpedia

    INDEX
    Explanations

    structured data elements or code syntax

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    -0.36
    目
    -0.31
    ตรี
    -0.31
    合わせて
    -0.31
    mi
    -0.31
    .
    -0.31
     quedando
    -0.31
     Schmid
    -0.30
    The
    -0.30
    ตา
    -0.30
    POSITIVE LOGITS
     nahilalakip
    0.93
     Roskov
    0.85
    ésultats
    0.85
     informée
    0.81
     Italijanski
    0.81
    FunctionFlags
    0.80
    ðsíða
    0.79
     autorytatywna
    0.79
    iſen
    0.79
    AndEndTag
    0.79
    Act Density 0.000%

    No Known Activations