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

    Neuronpedia

    INDEX
    Explanations

    pt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     constellation
    -0.06
    ์แ
    -0.06
    ทาน
    -0.06
     furthermore
    -0.06
     COLUMN
    -0.06
     conseg
    -0.06
     servic
    -0.06
     pursued
    -0.06
     haha
    -0.06
    ulton
    -0.06
    POSITIVE LOGITS
     //--
    0.07
    向
    0.07
     вак
    0.06
    Translator
    0.06
    �
    0.06
    ुप
    0.06
    定
    0.06
    Ship
    0.06
     Potion
    0.06
     وارد
    0.06
    Act Density 0.003%

    No Known Activations