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

    Neuronpedia

    INDEX
    Explanations

    tile flooring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.80
    pipe
    0.65
    questions
    0.65
     китай
    0.63
    z
    0.62
    a
    0.61
     v
    0.60
     Bill
    0.59
    quotes
    0.59
     Telegraph
    0.59
    POSITIVE LOGITS
    цаў
    0.70
    ोन
    0.60
    ιών
    0.58
    紛
    0.58
     trajectories
    0.57
     administrations
    0.57
    及
    0.57
     separations
    0.57
     biasing
    0.57
    脲
    0.57
    Act Density 0.003%

    No Known Activations