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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odian
    -0.07
     Portal
    -0.07
     divide
    -0.06
    ,model
    -0.06
     ов
    -0.06
     第一
    -0.06
    ORIGINAL
    -0.06
     Bolshevik
    -0.06
    лек
    -0.06
    リスト
    -0.06
    POSITIVE LOGITS
    !
↵
    0.06
     еп
    0.06
    มหานคร
    0.06
    мець
    0.06
     CURL
    0.06
     Mitarbeiter
    0.06
    _vect
    0.06
     scent
    0.06
    аз
    0.06
     Allies
    0.06
    Act Density 0.032%

    No Known Activations