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

    Neuronpedia

    INDEX
    Explanations

    Vader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bard
    -0.07
    僭
    -0.07
    堼
    -0.07
    拜师
    -0.07
    疥
    -0.07
    镆
    -0.06
    不具备
    -0.06
    浭
    -0.06
    戤
    -0.06
     lub
    -0.06
    POSITIVE LOGITS
     SYSTEM
    0.08
    StateChanged
    0.08
     Lim
    0.07
     Injector
    0.07
    افت
    0.07
     Dynamo
    0.07
     #=>
    0.07
    믹
    0.07
     choses
    0.07
     rejo
    0.07
    Act Density 0.000%

    No Known Activations