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

    Neuronpedia

    INDEX
    Explanations

    phrases that define or clarify concepts

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

    by which meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.57
    PerformLayout
    -0.54
     <<<<<<<<<<<<<<
    -0.49
     GreatSchools
    -0.46
     resourceCulture
    -0.46
    ContentAsync
    -0.45
    Πηγές
    -0.45
     مشين
    -0.45
    ConverterFactory
    -0.44
     виправивши
    -0.44
    POSITIVE LOGITS
     Mayr
    0.42
    AndroidJUnit
    0.40
     réguli
    0.39
     blessés
    0.39
    意思
    0.38
    saraba
    0.38
     Means
    0.36
     MEANS
    0.36
     अर्थ
    0.35
    psack
    0.35
    Act Density 0.045%

    No Known Activations