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

    Neuronpedia

    INDEX
    Explanations

    Time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jou
    -0.07
     ROS
    -0.07
    mamış
    -0.07
     Papa
    -0.07
     Scaffold
    -0.07
     defenses
    -0.07
    せる
    -0.07
     Cah
    -0.06
     Disco
    -0.06
     specialty
    -0.06
    POSITIVE LOGITS
    [max
    0.07
     ISBN
    0.06
    .tech
    0.06
    ใน
    0.06
    uring
    0.06
    (mean
    0.06
    juries
    0.06
     superhero
    0.06
     ○
    0.06
    ĩnh
    0.05
    Act Density 0.018%

    No Known Activations