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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .JScrollPane
    -0.06
    Entry
    -0.06
    perate
    -0.06
    ↵        
↵
    -0.06
    ustering
    -0.06
    ENV
    -0.06
     Times
    -0.06
     Korean
    -0.06
    _Message
    -0.06
    outedEventArgs
    -0.06
    POSITIVE LOGITS
    MER
    0.07
    علی
    0.07
     endpoint
    0.07
     minimum
    0.06
     fantastic
    0.06
    writes
    0.06
    rita
    0.06
    uilder
    0.06
     eylem
    0.06
     twitter
    0.06
    Act Density 0.020%

    No Known Activations