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

    Neuronpedia

    INDEX
    Explanations

    code syntax characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ps
    -0.07
    declare
    -0.07
     Αυ
    -0.07
    -front
    -0.07
     가지고
    -0.07
     //////////
    -0.06
     Carnival
    -0.06
    번
    -0.06
    _FE
    -0.06
     번
    -0.06
    POSITIVE LOGITS
    _fr
    0.07
     consciously
    0.06
     Agile
    0.06
     Marathon
    0.06
    网
    0.06
     Satan
    0.06
     filmer
    0.05
     ноября
    0.05
     Âu
    0.05
    ัวร
    0.05
    Act Density 0.083%

    No Known Activations