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

    Neuronpedia

    INDEX
    Explanations

    coalition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (activity
    -0.07
    Department
    -0.07
     Agriculture
    -0.06
     writeFile
    -0.06
    processed
    -0.06
    こんにちは
    -0.06
     Emirates
    -0.06
    azure
    -0.06
    лати
    -0.06
     заяви
    -0.06
    POSITIVE LOGITS
     \@
    0.07
     barracks
    0.06
    окон
    0.06
     cattle
    0.06
    mez
    0.06
     Dodge
    0.06
     zeit
    0.06
    152
    0.06
     stag
    0.05
    slow
    0.05
    Act Density 0.040%

    No Known Activations