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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ud
    -0.07
    .uuid
    -0.07
    .Usuario
    -0.07
     краї
    -0.07
     번
    -0.07
     experiencia
    -0.07
     pais
    -0.07
     VARIANT
    -0.07
    �性
    -0.07
    _DETECT
    -0.07
    POSITIVE LOGITS
    >
↵
↵
    0.08
     cigarette
    0.07
    191
    0.07
     Catholic
    0.07
    Рµ
    0.06
    Flo
    0.06
     optimal
    0.06
    //
↵
↵
    0.06
     perfectly
    0.06
    .sqlite
    0.06
    Act Density 0.010%

    No Known Activations