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

    Neuronpedia

    INDEX
    Explanations

    file extensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    άς
    -0.06
    Thông
    -0.06
    GetMapping
    -0.06
    اما
    -0.06
     Berm
    -0.06
     eks
    -0.06
    ZD
    -0.06
     Díky
    -0.06
     д
    -0.06
     cohort
    -0.06
    POSITIVE LOGITS
    rench
    0.07
    .DB
    0.06
     cable
    0.06
    .age
    0.06
     subtle
    0.06
    ↵            ↵
    0.06
     flo
    0.06
     Hog
    0.06
     blij
    0.06
     sext
    0.06
    Act Density 0.020%

    No Known Activations