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

    Neuronpedia

    INDEX
    Explanations

    treasury asset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ER
    0.59
    etition
    0.50
    ocardial
    0.47
    AN
    0.47
    icked
    0.47
    ense
    0.46
     Urban
    0.46
    ury
    0.46
    ick
    0.46
    Vegan
    0.46
    POSITIVE LOGITS
     adver
    0.54
     coprodu
    0.52
     chaper
    0.50
     conver
    0.50
     INTERVAL
    0.50
     amm
    0.49
     fluctuates
    0.49
     rapporti
    0.48
     mux
    0.48
     chairs
    0.48
    Act Density 0.000%

    No Known Activations