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

    Neuronpedia

    INDEX
    Explanations

    Missing default argument errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尹
    -0.06
     номер
    -0.06
    	describe
    -0.06
     contrib
    -0.06
    脑袋
    -0.06
    璀
    -0.06
     düzenlen
    -0.06
     toaster
    -0.06
    高贵
    -0.06
     wyświetl
    -0.06
    POSITIVE LOGITS
     sulfate
    0.08
     pharmacies
    0.08
     outfield
    0.07
    优势
    0.07
    aises
    0.07
     ".";↵
    0.07
    𝚠
    0.07
    cac
    0.07
    _singleton
    0.07
    情緒
    0.07
    Act Density 0.040%

    No Known Activations