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

    Neuronpedia

    INDEX
    Explanations

    dataset, tuple, Nations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eking
    0.54
    venuto
    0.49
    achery
    0.46
    acki
    0.46
     erlebt
    0.46
     হত্যাকা
    0.45
    etição
    0.45
    ڦ
    0.45
    года
    0.44
    專業
    0.44
    POSITIVE LOGITS
    a
    0.59
    ing
    0.55
    한
    0.46
    help
    0.46
     Cos
    0.46
    in
    0.45
    none
    0.45
    های
    0.44
    of
    0.43
    present
    0.43
    Act Density 0.001%

    No Known Activations