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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and attributes in the document

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

    Tokens preceding HTML span tags

    np_acts-logits-general · gemini-2.0-flash

    html span tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.61
    =$?
    -0.56
    echi
    -0.54
     Hein
    -0.54
    ditch
    -0.53
     Fletcher
    -0.53
     Stal
    -0.52
     Sere
    -0.52
    heri
    -0.51
    cene
    -0.50
    POSITIVE LOGITS
    span
    1.58
     span
    1.51
     Span
    1.50
    Span
    1.36
     SPAN
    1.16
     spans
    1.11
    SPAN
    1.04
     spanned
    0.99
    spans
    0.98
     spanning
    0.93
    Act Density 0.073%

    No Known Activations