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

    Neuronpedia

    INDEX
    Explanations

    references to ground truth data and its comparisons in experimental contexts

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

    ground truth comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.52
    IonicModule
    -0.51
    InputBorder
    -0.51
     allAfrica
    -0.45
     OFDb
    -0.44
     Paglinawan
    -0.43
    Muta
    -0.42
     okuyayım
    -0.41
     kaarangay
    -0.40
    -0.40
    POSITIVE LOGITS
     nakalista
    0.42
     graciosas
    0.37
     measured
    0.35
    ->___
    0.34
    REAS
    0.33
    javax
    0.33
    JSONException
    0.33
     Investigaciones
    0.33
    anganan
    0.33
    rateur
    0.32
    Act Density 0.131%

    No Known Activations