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

    Neuronpedia

    INDEX
    Explanations

    Example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     усп
    -0.07
     retrie
    -0.07
     responsibly
    -0.07
     verge
    -0.07
     waypoints
    -0.07
    ogs
    -0.07
    ook
    -0.06
    ед
    -0.06
     withheld
    -0.06
     collecting
    -0.06
    POSITIVE LOGITS
    Mode
    0.07
    (matrix
    0.06
    Sortable
    0.06
    险
    0.06
    prog
    0.06
    .Raw
    0.06
     अ
    0.06
    -that
    0.06
    .TabControl
    0.06
     إد
    0.06
    Act Density 0.282%

    No Known Activations