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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Background
    -0.07
    łó
    -0.07
    ลอ
    -0.07
    初三
    -0.07
    资源共享
    -0.06
     zamów
    -0.06
     Urs
    -0.06
     işlemleri
    -0.06
    expired
    -0.06
    滟
    -0.06
    POSITIVE LOGITS
    _FLOW
    0.07
     blade
    0.07
    Saving
    0.07
    条款
    0.07
    0.07
     communities
    0.07
    IsActive
    0.07
    携
    0.07
     args
    0.07
     和
    0.07
    Act Density 0.011%

    No Known Activations