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

    Neuronpedia

    INDEX
    Explanations

    technical vocabulary related to engineering and mechanics

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

    Following the word "uses" or "using"

    np_acts-logits-general · gemini-2.0-flash

    how it works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :+:
    -0.62
    FieldBuilder
    -0.58
    labus
    -0.57
    jména
    -0.56
     otomatig
    -0.55
     Exactos
    -0.54
    webElementXpaths
    -0.53
     Normdatei
    -0.53
     wireType
    -0.53
     demais
    -0.52
    POSITIVE LOGITS
     instead
    0.81
    instead
    0.74
    Instead
    0.72
     Instead
    0.70
    原理
    0.59
     вместо
    0.55
     istället
    0.53
     inherently
    0.52
     BorderSide
    0.51
    Obrázky
    0.51
    Act Density 1.076%

    No Known Activations