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

    Neuronpedia

    INDEX
    Explanations

    independent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ders
    -0.07
     websites
    -0.06
     authors
    -0.06
     forsk
    -0.06
     outsourcing
    -0.06
     Damen
    -0.06
     laz
    -0.06
    :
↵
↵
    -0.06
     lovers
    -0.06
    oogle
    -0.06
    POSITIVE LOGITS
    대행
    0.07
     grand
    0.06
    키
    0.06
    ูก
    0.06
    entic
    0.06
    ��
    0.06
    directive
    0.06
    ,/
    0.06
    co
    0.06
    指
    0.06
    Act Density 0.003%

    No Known Activations