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

    Neuronpedia

    INDEX
    Explanations

    Dialogue snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    necessarily
    -0.09
    -period
    -0.08
     이러한
    -0.08
    etheless
    -0.08
     atë
    -0.07
     foregoing
    -0.07
    λάχισ
    -0.07
    -fields
    -0.07
     thereafter
    -0.07
     นี้
    -0.07
    POSITIVE LOGITS
     Hey
    0.09
     bustling
    0.09
     middag
    0.08
     chilly
    0.08
     perplex
    0.08
     wakes
    0.08
    ämmer
    0.08
     hör
    0.08
     chilled
    0.08
     serene
    0.08
    Act Density 0.022%

    No Known Activations