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

    Neuronpedia

    INDEX
    Explanations

    Index/rating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Movie
    -0.07
    (Book
    -0.07
    .querySelector
    -0.07
    Entity
    -0.06
    learn
    -0.06
    apore
    -0.06
    emble
    -0.06
     Wednesday
    -0.06
     Stats
    -0.06
    .RestController
    -0.06
    POSITIVE LOGITS
     Barker
    0.07
    ระด
    0.07
     gid
    0.06
     слишком
    0.06
     xmm
    0.06
     hoses
    0.06
    (shape
    0.06
    .Style
    0.06
    都不
    0.06
    .function
    0.06
    Act Density 0.022%

    No Known Activations