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

    Neuronpedia

    INDEX
    Explanations

    note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Survivor
    -0.08
    .course
    -0.07
    钷
    -0.07
    �
    -0.07
    תוספת
    -0.07
     Crop
    -0.07
    汁
    -0.06
     bos
    -0.06
     morning
    -0.06
     rushed
    -0.06
    POSITIVE LOGITS
    جتماعية
    0.07
    Opcode
    0.07
     العلاقات
    0.07
    Digital
    0.06
     Raised
    0.06
    占据
    0.06
    证件
    0.06
    وا
    0.06
    ITHUB
    0.06
    CHASE
    0.06
    Act Density 0.011%

    No Known Activations