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
    OMETRY
    -0.06
     flour
    -0.06
     آمد
    -0.06
     position
    -0.06
    ören
    -0.06
     Tool
    -0.06
    γκο
    -0.06
    OBJECT
    -0.06
     Dion
    -0.06
     وقت
    -0.06
    POSITIVE LOGITS
     Rockefeller
    0.07
    ICIAL
    0.06
    ươi
    0.06
     bk
    0.06
    猫
    0.06
     $↵
    0.06
    lanmıştır
    0.06
     rozhod
    0.06
    يكا
    0.06
    �
    0.06
    Act Density 0.005%

    No Known Activations