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

    Neuronpedia

    INDEX
    Explanations

    legal and technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ген
    -0.07
    dma
    -0.06
     chest
    -0.06
    andan
    -0.06
    stanbul
    -0.06
    itura
    -0.06
    ини
    -0.06
     جامع
    -0.05
     değiş
    -0.05
    eni
    -0.05
    POSITIVE LOGITS
    련
    0.08
     _↵
    0.07
    ]]↵
    0.07
    ');?>↵
    0.07
     인터
    0.07
    awei
    0.07
    '=>$
    0.07
    ーネ
    0.06
     obtains
    0.06
    //!↵
    0.06
    Act Density 0.004%

    No Known Activations