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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phoenix
    -0.07
    NSIndexPath
    -0.07
    弭
    -0.07
    ][:
    -0.07
    -twitter
    -0.07
     euro
    -0.07
     �
    -0.07
     BaseEntity
    -0.07
     PHYS
    -0.07
    首先
    -0.07
    POSITIVE LOGITS
    är
    0.07
    工资
    0.07
    赖
    0.07
     auction
    0.07
    WARN
    0.07
    Forge
    0.07
    BL
    0.07
    beer
    0.06
    achine
    0.06
    嶂
    0.06
    Act Density 0.000%

    No Known Activations