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

    Neuronpedia

    INDEX
    Explanations

    Ct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dorm
    -0.07
     Wouldn
    -0.07
    Writing
    -0.07
    (pk
    -0.07
     Latest
    -0.07
     Bild
    -0.07
     Table
    -0.07
     dorm
    -0.07
    .Total
    -0.06
     ارد
    -0.06
    POSITIVE LOGITS
    екти
    0.07
    CRM
    0.06
    ασ
    0.06
    нят
    0.06
    .AllowGet
    0.06
     tel
    0.06
    gay
    0.06
    abies
    0.06
    чет
    0.06
     '/');↵
    0.06
    Act Density 0.002%

    No Known Activations