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

    Neuronpedia

    INDEX
    Explanations

    memory techniques

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     citizenship
    -0.08
     hátt
    -0.08
     healing
    -0.07
     bonding
    -0.07
     Healing
    -0.07
    peaker
    -0.07
     censorship
    -0.07
     demokrat
    -0.07
     swell
    -0.07
     dissolved
    -0.07
    POSITIVE LOGITS
     помещений
    0.08
     помещения
    0.08
     faria
    0.08
    .fake
    0.08
     স্থান
    0.08
     entlang
    0.08
     établissements
    0.08
    栋
    0.08
     Häuser
    0.08
     nyumba
    0.07
    Act Density 0.001%

    No Known Activations