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

    Neuronpedia

    INDEX
    Explanations

    2000 census

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Transactional
    -0.07
    аном
    -0.07
    fix
    -0.07
    seat
    -0.06
    μέν
    -0.06
     predictions
    -0.06
    ungan
    -0.06
    abb
    -0.06
    誌
    -0.06
    هن
    -0.06
    POSITIVE LOGITS
     emblem
    0.06
     affirm
    0.06
     opport
    0.06
    .Character
    0.06
     err
    0.06
    .Web
    0.06
    、↵↵
    0.06
     rejection
    0.06
     lambda
    0.06
    (food
    0.06
    Act Density 0.010%

    No Known Activations