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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    良
    -0.07
     रहन
    -0.07
     良
    -0.06
     Nathan
    -0.06
    osphere
    -0.06
    してる
    -0.06
     bisa
    -0.06
     Baş
    -0.06
     France
    -0.06
    POSITIVE LOGITS
    ريد
    0.07
    ="../
    0.07
     Victim
    0.07
    ('{{
    0.06
     расс
    0.06
     pot
    0.06
    wyn
    0.06
    urities
    0.06
    /Desktop
    0.06
    .Exceptions
    0.06
    Act Density 0.001%

    No Known Activations