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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Сергей
    -0.08
    >An
    -0.07
     торг
    -0.07
    .Sort
    -0.07
    .asc
    -0.07
    干部职工
    -0.07
    أن
    -0.07
     문제가
    -0.07
    .about
    -0.07
    _Delete
    -0.07
    POSITIVE LOGITS
    洞察
    0.07
    iffs
    0.07
    [attr
    0.07
     Enumerator
    0.07
    .height
    0.06
    ATION
    0.06
     reload
    0.06
    热搜
    0.06
    三条
    0.06
     advisors
    0.06
    Act Density 0.252%

    No Known Activations