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

    Neuronpedia

    INDEX
    Explanations

    towards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sustainable
    -0.07
    yme
    -0.07
     insurers
    -0.07
    勇
    -0.06
     disparities
    -0.06
    ประช
    -0.06
    Structured
    -0.06
    ası
    -0.06
     uniqueness
    -0.06
    切り
    -0.06
    POSITIVE LOGITS
    leyen
    0.07
     CONDITION
    0.06
    Yesterday
    0.06
     display
    0.06
     SHOP
    0.06
    лаж
    0.06
     behaves
    0.06
    UM
    0.06
     Telerik
    0.06
    AN
    0.06
    Act Density 0.000%

    No Known Activations