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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to calculations and evaluations in scientific contexts

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

    followed by how something is solved/evaluated

    np_acts-logits-general · gemini-2.0-flash

    solving, calculating, evaluating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.58
    rostis
    -0.57
    enumi
    -0.56
    чатки
    -0.56
     оригіналу
    -0.55
    ⓧ
    -0.55
     barbati
    -0.55
    lightly
    -0.54
     חיצוניים
    -0.54
    ($__
    -0.53
    POSITIVE LOGITS
     Meksiku
    0.61
    AndEndTag
    0.61
    WriteTagHelper
    0.53
     suing
    0.52
    AddTagHelper
    0.50
     analytically
    0.48
    laient
    0.48
     univ
    0.47
    Controllo
    0.47
    ראלי
    0.46
    Act Density 1.482%

    No Known Activations