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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to questioning or specifying identity and definitions

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

    which or what questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nEnter
    -0.58
    mored
    -0.49
    thmetic
    -0.45
    brood
    -0.44
     steckt
    -0.41
    phalt
    -0.40
     Frie
    -0.39
     
    -0.39
    rawDesc
    -0.39
    ьажоргаш
    -0.38
    POSITIVE LOGITS
     cual
    1.44
     cuales
    1.26
     quale
    1.13
    Cuál
    0.90
     quali
    0.86
     Cual
    0.85
     οποίο
    0.85
     οποία
    0.85
     lequel
    0.84
     cuál
    0.84
    Act Density 0.002%

    No Known Activations