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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ّا
    -0.07
    plate
    -0.06
    **/↵
    -0.06
    attack
    -0.06
     orta
    -0.06
     da
    -0.06
    Fetch
    -0.06
     آغاز
    -0.06
    _Group
    -0.06
    そんな
    -0.06
    POSITIVE LOGITS
     приня
    0.06
     zajímav
    0.06
     unavoidable
    0.06
     reconstruct
    0.06
    rb
    0.06
     respectful
    0.06
    ере
    0.06
    サイ
    0.06
     rq
    0.06
    عه
    0.06
    Act Density 0.071%

    No Known Activations