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

    Neuronpedia

    INDEX
    Explanations

    intro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solitaire
    -0.08
     Schwer
    -0.08
     CPPUNIT
    -0.08
     schizophrenia
    -0.08
     Nepal
    -0.08
    双色球
    -0.08
     pilgrimage
    -0.08
    世界杯
    -0.08
    Unicode
    -0.08
     Pathfinder
    -0.08
    POSITIVE LOGITS
    Outro
    0.10
     Outro
    0.10
    paque
    0.09
     afscheid
    0.09
     thanking
    0.09
     goodbye
    0.09
    /drop
    0.08
    _dropout
    0.08
    _prompt
    0.08
     disclosures
    0.08
    Act Density 0.014%

    No Known Activations