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

    Neuronpedia

    INDEX
    Explanations

    listing places and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    quir
    0.56
    Clic
    0.50
    Sí
    0.47
    кі
    0.47
    кли
    0.46
    Não
    0.45
    렌
    0.44
    ба
    0.44
    Однако
    0.44
    istos
    0.44
    POSITIVE LOGITS
     Updates
    0.58
     Outdoors
    0.56
     mqtt
    0.55
     Cycling
    0.55
     Data
    0.54
     Outdoor
    0.53
     Update
    0.52
     Reference
    0.52
     Trains
    0.52
     Oil
    0.51
    Act Density 0.000%

    No Known Activations