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

    Neuronpedia

    INDEX
    Explanations

    Talking/Discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    استان
    -0.07
     milfs
    -0.07
     quieres
    -0.06
    Boundary
    -0.06
     midterm
    -0.06
    ันยายน
    -0.06
     cinco
    -0.06
    рогра
    -0.06
    .am
    -0.06
    お
    -0.06
    POSITIVE LOGITS
    cell
    0.07
     claims
    0.07
     госп
    0.06
    고
    0.06
    gnore
    0.06
     catastrophe
    0.06
     Buddh
    0.06
    ้ม
    0.06
     alertController
    0.06
    acak
    0.06
    Act Density 0.002%

    No Known Activations