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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Relief
    -0.07
    能得到
    -0.07
     consolidation
    -0.07
    :event
    -0.07
     Downtown
    -0.07
    FragmentManager
    -0.07
     decide
    -0.06
    ceeded
    -0.06
     وإن
    -0.06
    感觉自己
    -0.06
    POSITIVE LOGITS
    ха
    0.07
    ap
    0.07
    分布
    0.07
     них
    0.07
    往来
    0.06
    Absent
    0.06
     else
    0.06
     ка
    0.06
    habit
    0.06
     assorted
    0.06
    Act Density 0.004%

    No Known Activations