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

    Neuronpedia

    INDEX
    Explanations

    arrests and detentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    려
    -0.07
    ￣￣
    -0.07
     회사
    -0.06
    험
    -0.06
     standart
    -0.06
    Leap
    -0.06
    anyl
    -0.06
     subsystem
    -0.06
     containment
    -0.06
     вариант
    -0.06
    POSITIVE LOGITS
     cherished
    0.06
     magician
    0.06
    сли
    0.06
     softball
    0.06
     literacy
    0.06
     Barrier
    0.06
     دوباره
    0.06
     افزار
    0.06
     Publications
    0.06
    #error
    0.06
    Act Density 0.046%

    No Known Activations