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

    Neuronpedia

    INDEX
    Explanations

    ground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     key
    -0.07
     Folder
    -0.06
     maternal
    -0.06
     Ed
    -0.06
     Most
    -0.06
     DESC
    -0.06
     Điều
    -0.06
     causal
    -0.06
     CAP
    -0.06
    User
    -0.06
    POSITIVE LOGITS
     underground
    0.16
     Underground
    0.13
    地下
    0.08
     subway
    0.07
    ground
    0.07
     downstairs
    0.07
     unpleasant
    0.06
    PHONE
    0.06
    eggies
    0.06
     indoor
    0.06
    Act Density 0.003%

    No Known Activations