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
    �
    -0.07
     solitary
    -0.07
     spot
    -0.06
     nemá
    -0.06
    _tables
    -0.06
     distributing
    -0.06
     publik
    -0.06
     garments
    -0.06
     ↵		↵
    -0.06
    代理
    -0.06
    POSITIVE LOGITS
     روسی
    0.08
    더니
    0.07
     //================================================================
    0.07
    prech
    0.07
     IPCC
    0.07
    なの
    0.07
    aler
    0.07
    breadcrumbs
    0.06
    rieg
    0.06
    _theta
    0.06
    Act Density 0.003%

    No Known Activations