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

    Neuronpedia

    INDEX
    Explanations

    Code/file paths/errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nin
    -0.08
     ścian
    -0.07
    ינם
    -0.07
     �
    -0.07
     dispar
    -0.07
     السل
    -0.07
     Ty
    -0.07
    ἀ
    -0.06
    �
    -0.06
    INTER
    -0.06
    POSITIVE LOGITS
     touching
    0.07
    现在
    0.07
     guarantees
    0.07
    ,buf
    0.07
    部队
    0.07
     Lesson
    0.07
     Emirates
    0.07
    Student
    0.06
    鸳
    0.06
     station
    0.06
    Act Density 0.011%

    No Known Activations