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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    噴
    -0.07
    .Double
    -0.07
    草案
    -0.07
     прид
    -0.06
    apsed
    -0.06
    (dy
    -0.06
     לישראל
    -0.06
    洑
    -0.06
    InvalidOperationException
    -0.06
    提
    -0.06
    POSITIVE LOGITS
    choices
    0.08
     poultry
    0.07
    同じ
    0.07
    dt
    0.07
     breweries
    0.07
    ,,,,,,,,
    0.07
    Addr
    0.07
     двух
    0.07
     Resort
    0.07
    album
    0.06
    Act Density 0.001%

    No Known Activations