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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that denote inclusivity or universality

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

    any other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.46
     ujednoznacz
    -0.43
    Život
    -0.43
    Short
    -0.41
    pyplot
    -0.40
    Política
    -0.39
    Dead
    -0.38
    CppMethod
    -0.37
     Dead
    -0.37
     today
    -0.36
    POSITIVE LOGITS
     other
    0.60
     demás
    0.56
     others
    0.51
    #+#
    0.50
     demais
    0.49
    others
    0.46
     ***!
    0.46
    الدراسه
    0.46
     autres
    0.45
     diğer
    0.44
    Act Density 0.020%

    No Known Activations