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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bfs
    -0.07
     supern
    -0.07
    _);
↵
    -0.07
    بني
    -0.07
    BASE
    -0.06
     }
↵
↵
↵
    -0.06
    쐬
    -0.06
    yg
    -0.06
    (agent
    -0.06
     conveyor
    -0.06
    POSITIVE LOGITS
     plais
    0.07
    ante
    0.07
    ceipt
    0.07
    หอม
    0.07
    的独特
    0.07
    涑
    0.07
     Stam
    0.07
    匣
    0.07
     ràng
    0.07
    zed
    0.06
    Act Density 0.025%

    No Known Activations