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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     régal
    -0.56
    <bos>
    -0.52
    sspiel
    -0.52
    олові
    -0.51
    rollo
    -0.50
    demort
    -0.50
    verwijspagina
    -0.49
     istri
    -0.49
    uoco
    -0.49
    drawiam
    -0.49
    POSITIVE LOGITS
    sizeCache
    0.59
    IntoConstraints
    0.53
    MessageOf
    0.52
    TagHelper
    0.52
    NameInMap
    0.51
     administration
    0.51
    PreferredItem
    0.50
    SaveChangesAsync
    0.48
     proper
    0.48
    Chham
    0.47
    Act Density 0.117%

    No Known Activations