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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ATK
    -0.07
    执
    -0.07
    atemala
    -0.07
    _OT
    -0.07
    stitial
    -0.07
    /global
    -0.07
    (nt
    -0.07
    ену
    -0.06
     Grant
    -0.06
    /ic
    -0.06
    POSITIVE LOGITS
    Outlined
    0.06
     {↵↵↵
    0.06
    rgba
    0.06
     сло
    0.06
     очень
    0.06
     Size
    0.06
    yu
    0.06
     समय
    0.06
     diffuse
    0.06
     duplicate
    0.05
    Act Density 0.003%

    No Known Activations