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

    Neuronpedia

    INDEX
    Explanations

    Access modifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蓏
    -0.07
    .SO
    -0.07
    уд
    -0.06
     appetite
    -0.06
    菘
    -0.06
     мя
    -0.06
     UObject
    -0.06
    own
    -0.06
    itable
    -0.06
     ATL
    -0.06
    POSITIVE LOGITS
     lorem
    0.08
    记者
    0.08
     recruiter
    0.07
     restrict
    0.07
    ゆっくり
    0.07
    .Repositories
    0.07
     contexto
    0.07
    首届
    0.07
     erotico
    0.07
    Bitte
    0.07
    Act Density 0.001%

    No Known Activations