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

    Neuronpedia

    INDEX
    Explanations

    quantitative/qualitative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reign
    -0.07
     Lloyd
    -0.07
    Stan
    -0.06
    ué
    -0.06
     memory
    -0.06
     traps
    -0.06
    cers
    -0.06
    Mil
    -0.06
     tor
    -0.06
    RFC
    -0.06
    POSITIVE LOGITS
     quantitative
    0.12
     쓰
    0.08
    (UnityEngine
    0.07
    .Relative
    0.07
     воздуха
    0.07
     Supplementary
    0.07
    _mob
    0.06
    .addRow
    0.06
     BitConverter
    0.06
     Mane
    0.06
    Act Density 0.003%

    No Known Activations