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

    Neuronpedia

    INDEX
    Explanations

    team

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ीदव
    -0.07
    ูงส
    -0.06
    προ
    -0.06
     �
    -0.06
    ọn
    -0.06
    �
    -0.06
     comme
    -0.06
    .displayName
    -0.06
    软件
    -0.06
    			
↵			
↵
    -0.06
    POSITIVE LOGITS
     Elizabeth
    0.07
     Carol
    0.07
    factor
    0.06
     ////
    0.06
     disappears
    0.06
    ova
    0.06
    plays
    0.06
     Jim
    0.06
    παίδ
    0.06
     /^(
    0.06
    Act Density 0.000%

    No Known Activations