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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulent
    -0.08
     fitted
    -0.08
    -0.07
     connected
    -0.07
    .Url
    -0.07
     simultaneously
    -0.07
    ialis
    -0.07
     explos
    -0.07
    れる
    -0.07
    Cri
    -0.07
    POSITIVE LOGITS
    申
    0.09
     Already
    0.09
    이미
    0.08
     ఇప్పటికే
    0.08
     sudah
    0.08
     уже
    0.08
    овы
    0.08
     docket
    0.08
     imig
    0.08
    ాడు
    0.08
    Act Density 0.061%
    No Known Activations