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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     têm
    -0.07
     EO
    -0.07
    ΅
    -0.07
    Ủ
    -0.07
    ср
    -0.07
    _IO
    -0.06
    )!↵
    -0.06
    肪
    -0.06
     ,
↵
    -0.06
     number
    -0.06
    POSITIVE LOGITS
    (theta
    0.08
    -on
    0.07
    した
    0.07
     shocks
    0.07
     SwiftUI
    0.07
     sidebar
    0.07
     split
    0.07
     כמה
    0.07
    (chart
    0.06
    ->{
    0.06
    Act Density 0.003%

    No Known Activations