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

    Neuronpedia

    INDEX
    Explanations

    discussions emphasizing multiple perspectives and beliefs

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

    multiple perspectives and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wicidata
    -0.61
    ۜ
    -0.58
     дописавши
    -0.58
     ***!
    -0.52
     للمعارف
    -0.50
     Hand
    -0.50
     kasarigan
    -0.47
    __':
    -0.45
     hand
    -0.44
    __':
    -0.44
    POSITIVE LOGITS
     createState
    0.43
     içinde
    0.42
     externi
    0.36
     bluzka
    0.35
     arguments
    0.35
     opposing
    0.34
     Meinung
    0.34
     Tinggi
    0.34
     vulgares
    0.34
    zaar
    0.34
    Act Density 0.091%

    No Known Activations