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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aders
    -0.08
     borough
    -0.07
    �
    -0.07
    ることができ
    -0.07
     кто
    -0.06
    .Load
    -0.06
     cooperating
    -0.06
    students
    -0.06
     Seah
    -0.06
    蹶
    -0.06
    POSITIVE LOGITS
    詹
    0.07
    Fred
    0.06
     det
    0.06
    (exception
    0.06
    rij
    0.06
     hinge
    0.06
    合适
    0.06
    福利
    0.06
    -X
    0.06
    ections
    0.06
    Act Density 0.082%

    No Known Activations