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

    Neuronpedia

    INDEX
    Explanations

    strengthening international relations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    昡
    -0.07
    uliar
    -0.07
    cadena
    -0.07
    _servers
    -0.07
    Detect
    -0.07
    .headers
    -0.07
    bler
    -0.07
     deleg
    -0.07
    Authorities
    -0.07
    DDS
    -0.07
    POSITIVE LOGITS
    创造了
    0.07
    品质
    0.06
    .m
    0.06
    t
    0.06
    فناد
    0.06
    城墙
    0.06
    하였
    0.06
    ]."
    0.06
    랐
    0.06
    ")))↵
    0.06
    Act Density 0.124%

    No Known Activations