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

    Neuronpedia

    INDEX
    Explanations

    words indicating relationships and comparisons between different concepts or entities

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

    "... alike with" or "as ... as possible"

    np_acts-logits-general · gemini-2.0-flash

    all time, alike, possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    -0.63
    ()");
    -0.58
    /');
    -0.54
    []
    -0.52
    ubo
    -0.51
     "));
    -0.51
     ")
    -0.50
    ']?>
    -0.50
    /
    -0.50
    "]}
    -0.49
    POSITIVE LOGITS
    BufferException
    0.82
    uxxxx
    0.78
    WriteTagHelper
    0.78
     Roskov
    0.77
    saraba
    0.76
    HostException
    0.76
     հղումներ
    0.75
    Poloha
    0.72
    Билгалдахарш
    0.70
    CodeAttribute
    0.70
    Act Density 0.700%

    No Known Activations