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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     telling
    -0.07
    "]').
    -0.07
     stopped
    -0.06
    extern
    -0.06
     Across
    -0.06
     RH
    -0.06
    .DO
    -0.06
    interface
    -0.06
    -transfer
    -0.06
    RH
    -0.06
    POSITIVE LOGITS
     buyer
    0.07
    HomeAsUpEnabled
    0.06
     ApplicationUser
    0.06
     FOOD
    0.06
     privateKey
    0.06
    顺
    0.06
    ignore
    0.06
     Moderate
    0.06
    LinkedIn
    0.06
     Ramsey
    0.06
    Act Density 0.001%

    No Known Activations