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

    Neuronpedia

    INDEX
    Explanations

    code snippets and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aisément
    0.44
     unequiv
    0.41
    𒅌
    0.40
     当然
    0.37
     informé
    0.37
    腔
    0.36
     expedite
    0.36
     unquestionably
    0.36
    政府采购
    0.36
    যজ্ঞ
    0.36
    POSITIVE LOGITS
     *:
    0.51
    ):
    0.49
    dll
    0.44
     '':
    0.44
     canadian
    0.44
     canada
    0.44
    *:
    0.43
     Calgary
    0.41
     $:
    0.41
     honda
    0.40
    Act Density 0.002%

    No Known Activations