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
    .att
    -0.07
     erad
    -0.07
    绽放
    -0.06
    -upload
    -0.06
    设计器
    -0.06
     blatantly
    -0.06
     duo
    -0.06
    _'.$
    -0.06
    萏
    -0.06
    全面提升
    -0.06
    POSITIVE LOGITS
    ri
    0.07
    lesi
    0.07
    葡萄牙
    0.07
     destin
    0.07
     instr
    0.07
     sources
    0.06
     ancestors
    0.06
    obi
    0.06
     }}>↵
    0.06
     parte
    0.06
    Act Density 0.021%

    No Known Activations