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

    Neuronpedia

    INDEX
    Explanations

    infections and immune responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hold
    -0.07
     |-
    -0.07
     Mt
    -0.07
    oves
    -0.07
    唑
    -0.07
     Train
    -0.07
    /engine
    -0.07
     XS
    -0.07
    Translated
    -0.06
     Kris
    -0.06
    POSITIVE LOGITS
    etypes
    0.08
    ものが
    0.07
    游戏当中
    0.07
    (tuple
    0.07
    IBUTES
    0.07
    -animation
    0.07
     melanch
    0.07
    굶
    0.07
    ixed
    0.07
    💵
    0.07
    Act Density 0.039%

    No Known Activations