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

    Neuronpedia

    INDEX
    Explanations

    English as a second language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tot
    -0.07
     перем
    -0.07
     yuk
    -0.07
     assum
    -0.07
     готов
    -0.07
    dens
    -0.06
     Cycle
    -0.06
    .DisplayName
    -0.06
    产生的
    -0.06
    倧
    -0.06
    POSITIVE LOGITS
    scriber
    0.07
    
    0.07
    ך
    0.07
    ,b
    0.07
    ,height
    0.06
    ;c
    0.06
     tiles
    0.06
    ác
    0.06
    遏
    0.06
    	layout
    0.06
    Act Density 0.103%

    No Known Activations