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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating additional information or context

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

    besides or without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Advance
    -0.38
     avoient
    -0.38
    checs
    -0.37
    polis
    -0.35
     bağlant
    -0.35
     encamin
    -0.35
     advance
    -0.34
     lanzamiento
    -0.34
    🇶
    -0.33
     montaña
    -0.33
    POSITIVE LOGITS
    rungsseite
    0.67
    AddTagHelper
    0.53
    OGND
    0.51
    HasAnnotation
    0.51
    abestanden
    0.49
     nahilalakip
    0.49
    webElementXpaths
    0.47
    GOTREF
    0.47
    sizeCache
    0.46
     contextLoads
    0.45
    Act Density 0.016%

    No Known Activations