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

    Neuronpedia

    INDEX
    Explanations

    technical processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (predict
    -0.07
    /arch
    -0.07
    (entries
    -0.06
    ex
    -0.06
    /full
    -0.06
     Sanayi
    -0.06
     trademark
    -0.06
    슈
    -0.06
     подв
    -0.06
    лоч
    -0.06
    POSITIVE LOGITS
    		
↵
    0.07
    心理
    0.06
     None
    0.06
    swagen
    0.06
    GLOBAL
    0.06
     qued
    0.06
     ファ
    0.06
     slated
    0.06
     　　　　　　
    0.06
    -pad
    0.06
    Act Density 0.233%

    No Known Activations