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
    jit
    -0.07
    .”↵↵↵↵
    -0.07
     Nail
    -0.07
    TZ
    -0.07
     freezing
    -0.07
     joint
    -0.07
     prend
    -0.06
    世界观
    -0.06
    зем
    -0.06
     black
    -0.06
    POSITIVE LOGITS
    稳固
    0.08
    ⡢
    0.08
    如果玩家
    0.07
    🚇
    0.07
    ควร
    0.07
    :{}
    0.07
    送料
    0.07
     ((__
    0.07
    "]').
    0.07
    핀
    0.07
    Act Density 0.007%

    No Known Activations