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

    Neuronpedia

    INDEX
    Explanations

    blooms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flows
    -0.63
     flows
    -0.63
     tas
    -0.58
     blooms
    -0.56
    MessageTagHelper
    -0.55
     Flows
    -0.52
    y
    -0.52
     useContext
    -0.51
    soka
    -0.50
    ljeno
    -0.50
    POSITIVE LOGITS
     leaſt
    0.72
     ſeveral
    0.69
     Theſe
    0.68
     leſs
    0.68
     Majefty
    0.66
     himſelf
    0.65
     Efq
    0.65
     ſmall
    0.64
    IndentedString
    0.64
     themſelves
    0.64
    Act Density 0.295%

    No Known Activations