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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns/possessives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    legs
    -0.06
     visiting
    -0.06
     amendments
    -0.06
     signatures
    -0.06
     Citation
    -0.06
     avenues
    -0.06
    Detect
    -0.06
    objs
    -0.05
    .cg
    -0.05
     určit
    -0.05
    POSITIVE LOGITS
    iele
    0.07
     squeeze
    0.07
    テ
    0.06
    的问题
    0.06
    accessToken
    0.06
     увид
    0.06
    (
↵
    0.06
     Quartz
    0.06
     pea
    0.06
    iese
    0.06
    Act Density 0.022%

    No Known Activations